diff --git a/.github/workflows/server.yml b/.github/workflows/server.yml
index f9aeefaa8..e385e03f3 100644
--- a/.github/workflows/server.yml
+++ b/.github/workflows/server.yml
@@ -47,6 +47,8 @@ jobs:
       - name: Clone
         id: checkout
         uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
 
       - name: Dependencies
         id: depends
@@ -58,7 +60,6 @@ jobs:
             cmake \
             python3-pip \
             wget \
-            psmisc \
             language-pack-en
 
       - name: Build
@@ -90,3 +91,46 @@ jobs:
         run: |
           cd examples/server/tests
           PORT=8888 ./tests.sh --stop --no-skipped --no-capture --tags slow
+
+
+  server-windows:
+    runs-on: windows-latest
+
+    steps:
+      - name: Clone
+        id: checkout
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      - name: Build
+        id: cmake_build
+        run: |
+          mkdir build
+          cd build
+          cmake ..  -DLLAMA_BUILD_SERVER=ON -DCMAKE_BUILD_TYPE=Release ;
+          cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS} --target server
+
+      - name: Python setup
+        id: setup_python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+
+      - name: Tests dependencies
+        id: test_dependencies
+        run: |
+          pip install -r examples/server/tests/requirements.txt
+
+      - name: Tests
+        id: server_integration_tests
+        run: |
+          cd examples/server/tests
+          behave.exe --summary --stop --no-capture --exclude 'issues|wrong_usages|passkey' --tags llama.cpp
+
+      - name: Slow tests
+        id: server_integration_tests_slow
+        if: ${{ github.event.schedule != '' || github.event.inputs.slow_tests == 'true' }}
+        run: |
+          cd examples/server/tests
+          behave.exe --stop --no-skipped --no-capture --tags slow
diff --git a/.gitignore b/.gitignore
index 5edb75607..1e45f89bb 100644
--- a/.gitignore
+++ b/.gitignore
@@ -32,6 +32,7 @@ models-mnt
 /embedding
 /gguf
 /gguf-llama-simple
+/gritlm
 /imatrix
 /infill
 /libllama.so
diff --git a/common/common.cpp b/common/common.cpp
index 66e40c50e..4edd36721 100644
--- a/common/common.cpp
+++ b/common/common.cpp
@@ -1853,3 +1853,18 @@ void dump_kv_cache_view_seqs(const llama_kv_cache_view & view, int row_size) {
 
     printf("\n=== Done dumping\n");
 }
+
+void llama_embd_normalize(const float * inp, float * out, int n) {
+    double sum = 0.0;
+    for (int i = 0; i < n; i++) {
+        sum += inp[i] * inp[i];
+    }
+    sum = sqrt(sum);
+
+    const float norm = sum > 0.0 ? 1.0f / sum : 0.0f;
+
+    for (int i = 0; i < n; i++) {
+        out[i] = inp[i] * norm;
+    }
+}
+
diff --git a/common/common.h b/common/common.h
index 411204dbf..829c04910 100644
--- a/common/common.h
+++ b/common/common.h
@@ -274,3 +274,10 @@ void dump_kv_cache_view(const llama_kv_cache_view & view, int row_size = 80);
 
 // Dump the KV cache view showing individual sequences in each cell (long output).
 void dump_kv_cache_view_seqs(const llama_kv_cache_view & view, int row_size = 40);
+
+//
+// Embedding utils
+//
+
+void llama_embd_normalize(const float * inp, float * out, int n);
+
diff --git a/common/grammar-parser.cpp b/common/grammar-parser.cpp
index bf89a96f3..2a1301569 100644
--- a/common/grammar-parser.cpp
+++ b/common/grammar-parser.cpp
@@ -278,6 +278,22 @@ namespace grammar_parser {
             while (*pos) {
                 pos = parse_rule(state, pos);
             }
+            // Validate the state to ensure that all rules are defined
+            for (const auto & rule : state.rules) {
+                for (const auto & elem : rule) {
+                    if (elem.type == LLAMA_GRETYPE_RULE_REF) {
+                        // Ensure that the rule at that location exists
+                        if (elem.value >= state.rules.size() || state.rules[elem.value].empty()) {
+                            // Get the name of the rule that is missing
+                            for (const auto & kv : state.symbol_ids) {
+                                if (kv.second == elem.value) {
+                                    throw std::runtime_error("Undefined rule identifier '" + kv.first + "'");
+                                }
+                            }
+                        }
+                    }
+                }
+            }
             return state;
         } catch (const std::exception & err) {
             fprintf(stderr, "%s: error parsing grammar: %s\n", __func__, err.what());
diff --git a/examples/CMakeLists.txt b/examples/CMakeLists.txt
index 653abc73a..e762cf8b9 100644
--- a/examples/CMakeLists.txt
+++ b/examples/CMakeLists.txt
@@ -20,6 +20,7 @@ else()
     add_subdirectory(convert-llama2c-to-ggml)
     add_subdirectory(embedding)
     add_subdirectory(finetune)
+    add_subdirectory(gritlm)
     add_subdirectory(infill)
     add_subdirectory(llama-bench)
     add_subdirectory(llava)
diff --git a/examples/benchmark/benchmark-matmult.cpp b/examples/benchmark/benchmark-matmult.cpp
index 8c48df00e..72fc025ed 100644
--- a/examples/benchmark/benchmark-matmult.cpp
+++ b/examples/benchmark/benchmark-matmult.cpp
@@ -190,12 +190,10 @@ int main(int argc, char ** argv)  {
 
     int32_t nelements = sizex*sizey;
 
-    std::vector<int64_t> hist_cur(1 << 4, 0);
-
     // Set up a the benchmark matrices
     // printf("Creating new tensor q11 & Running quantize\n");
     struct ggml_tensor * q11 = ggml_new_tensor_2d(ctx, qtype, sizex, sizey);
-    ggml_quantize_chunk(qtype, (const float *) m11->data, q11->data, 0, nelements/m11->ne[0], m11->ne[0], hist_cur.data(), nullptr);
+    ggml_quantize_chunk(qtype, (const float *) m11->data, q11->data, 0, nelements/m11->ne[0], m11->ne[0], nullptr);
 
     // Set up a the compute graph
     // printf("Creating new tensor q31\n");
@@ -208,7 +206,7 @@ int main(int argc, char ** argv)  {
     // Set up a second graph computation to make sure we override the CPU cache lines
     // printf("Creating new tensor q12 & Running quantize\n");
     struct ggml_tensor * q12 = ggml_new_tensor_2d(ctx, qtype, sizex, sizey);
-    ggml_quantize_chunk(qtype, (const float *) m12->data, q12->data, 0, nelements/m12->ne[0], m12->ne[0], hist_cur.data(), nullptr);
+    ggml_quantize_chunk(qtype, (const float *) m12->data, q12->data, 0, nelements/m12->ne[0], m12->ne[0], nullptr);
 
     // printf("Creating new tensor q32\n");
     struct ggml_tensor * q32 = ggml_mul_mat(ctx, q12, m2);
diff --git a/examples/embedding/embedding.cpp b/examples/embedding/embedding.cpp
index 4da81998a..530d89a4a 100644
--- a/examples/embedding/embedding.cpp
+++ b/examples/embedding/embedding.cpp
@@ -24,17 +24,6 @@ static void batch_add_seq(llama_batch & batch, const std::vector<int32_t> & toke
     }
 }
 
-static void normalize(const float * vec, float * out, int n) {
-    float norm = 0;
-    for (int i = 0; i < n; i++) {
-        norm += vec[i] * vec[i];
-    }
-    norm = sqrt(norm);
-    for (int i = 0; i < n; i++) {
-        out[i] = vec[i] / norm;
-    }
-}
-
 static void batch_decode(llama_context * ctx, llama_batch & batch, float * output, int n_seq, int n_embd) {
     // clear previous kv_cache values (irrelevant for embeddings)
     llama_kv_cache_clear(ctx);
@@ -45,7 +34,6 @@ static void batch_decode(llama_context * ctx, llama_batch & batch, float * outpu
         fprintf(stderr, "%s : failed to decode\n", __func__);
     }
 
-    // normalize on copy
     for (int i = 0; i < batch.n_tokens; i++) {
         if (!batch.logits[i]) {
             continue;
@@ -62,7 +50,7 @@ static void batch_decode(llama_context * ctx, llama_batch & batch, float * outpu
         }
 
         float * out = output + batch.seq_id[i][0] * n_embd;
-        normalize(embd, out, n_embd);
+        llama_embd_normalize(embd, out, n_embd);
     }
 }
 
diff --git a/examples/gritlm/CMakeLists.txt b/examples/gritlm/CMakeLists.txt
new file mode 100644
index 000000000..ac4a5ae79
--- /dev/null
+++ b/examples/gritlm/CMakeLists.txt
@@ -0,0 +1,5 @@
+set(TARGET gritlm)
+add_executable(${TARGET} gritlm.cpp)
+install(TARGETS ${TARGET} RUNTIME)
+target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
+target_compile_features(${TARGET} PRIVATE cxx_std_11)
diff --git a/examples/gritlm/gritlm.cpp b/examples/gritlm/gritlm.cpp
new file mode 100644
index 000000000..3d4b085d6
--- /dev/null
+++ b/examples/gritlm/gritlm.cpp
@@ -0,0 +1,229 @@
+#include "common.h"
+#include "llama.h"
+
+#include <string>
+#include <vector>
+
+// #define GRIT_DEBUG
+
+static float dot_product(const std::vector<float> & v1, const std::vector<float> & v2) {
+    float dot = 0.0f;
+    for (uint64_t i = 0; i < v1.size(); ++i) {
+        dot += v1[i] * v2[i];
+    }
+    return dot;
+}
+
+static float norm(const std::vector<float> & v) {
+    return std::sqrt(dot_product(v, v));
+}
+
+static float cosine_similarity(const std::vector<float> & v1, const std::vector<float> & v2) {
+    return dot_product(v1, v2) / (norm(v1) * norm(v2));
+}
+
+static std::vector<std::vector<float>> encode(llama_context * ctx, const std::vector<std::string> & sentences, const std::string & instruction) {
+    std::vector<std::vector<float>> result;
+
+    const llama_model * mdl = llama_get_model(ctx);
+
+    llama_batch batch = llama_batch_init(llama_n_batch(ctx), 0, 1);
+
+    for (uint64_t i = 0; i < sentences.size(); i++) {
+        llama_batch_clear(batch);
+
+        const std::string input_string = instruction + sentences[i];
+
+        std::vector<llama_token> inputs = llama_tokenize(mdl, input_string, true, false);
+
+        const int32_t n_toks = inputs.size();
+
+        // GritLM seems to have EOS = ""
+        // https://github.com/ContextualAI/gritlm/blob/92025b16534712b31b3c4aaaf069350e222bd5f8/gritlm/gritlm.py#L18
+        // inputs.push_back(llama_token_eos(mdl));
+
+        // we want to ignore instruction tokens for mean pooling
+        const int32_t n_inst = llama_tokenize(mdl, instruction, true, false).size();
+
+#ifdef GRIT_DEBUG
+        // debug tokens - should be matching as referenced in the GritLM sample
+        std::for_each(inputs.begin(), inputs.end(), [&ctx](llama_token t) {
+            std::printf("[%u:%s]", t, llama_token_to_piece(ctx, t).c_str());
+        });
+        std::printf("\n");
+#endif
+
+        // add input to batch (this increments n_tokens)
+        for (int32_t j = 0; j < n_toks; j++) {
+            llama_batch_add(batch, inputs[j], j, { 0 }, j >= n_inst);
+        }
+
+        // clear previous kv_cache values (irrelevant for embeddings)
+        llama_kv_cache_clear(ctx);
+        llama_set_causal_attn(ctx, false);
+
+        // run model
+        llama_decode(ctx, batch);
+
+        // get embedding dimensions
+        uint64_t n_embd = llama_n_embd(mdl);
+
+        // allocate embedding output
+        std::vector<float> emb_unorm(n_embd, 0.0f);
+
+        // sum up all token embeddings
+        for (int32_t k = n_inst; k < n_toks; k++) {
+            float * emb = llama_get_embeddings_ith(ctx, k);
+            for (uint64_t j = 0; j < n_embd; j++) {
+                emb_unorm[j] += emb[j];
+            }
+        }
+
+        // divide by number of tokens (mean pooling)
+        {
+            const uint64_t n_sent = n_toks - n_inst;
+
+            for (uint64_t j = 0; j < n_embd; j++) {
+                emb_unorm[j] /= n_sent;
+            }
+        }
+
+        std::vector<float> emb_norm(emb_unorm.size());
+        llama_embd_normalize(emb_unorm.data(), emb_norm.data(), n_embd);
+        result.push_back(emb_norm);
+
+#ifdef GRIT_DEBUG
+        // print out emb_norm
+        std::printf("embedding %ld: ", i);
+        for (uint64_t j = 0; j < n_embd; j++) {
+            std::printf("%.5f ", emb_norm[j]);
+        }
+        std::printf("\n\n");
+#endif
+    }
+
+    llama_batch_free(batch);
+
+    return result;
+}
+
+static std::string generate(llama_context * ctx, const std::string & prompt, bool stream) {
+    std::string result;
+
+    const llama_model * mdl = llama_get_model(ctx);
+    llama_token eos_token = llama_token_eos(mdl);
+
+    llama_kv_cache_clear(ctx);
+    llama_set_causal_attn(ctx, true);
+    llama_batch bat = llama_batch_init(llama_n_batch(ctx), 0, 1);
+
+    std::vector<llama_token> inputs = llama_tokenize(mdl, prompt, false, true);
+    int32_t i_current_token = 0;
+
+    while (true) {
+        llama_batch_clear(bat);
+        auto n_inputs = (int32_t)inputs.size();
+        for (int32_t i = 0; i < n_inputs; i++) {
+            llama_batch_add(bat, inputs[i], i_current_token++, { 0 }, i == n_inputs - 1);
+        }
+        inputs.clear();
+
+        llama_decode(ctx, bat);
+        auto logits = llama_get_logits_ith(ctx, bat.n_tokens - 1);
+
+        auto candidates = std::vector<llama_token_data>(llama_n_vocab(mdl));
+        auto n_candidates = (int32_t)candidates.size();
+        for (int32_t token = 0; token < n_candidates; token++) {
+            candidates[token] = llama_token_data{ token, logits[token], 0.0f };
+        }
+        auto candidates_p = llama_token_data_array{ candidates.data(), candidates.size(), false };
+
+        llama_token token = llama_sample_token_greedy(ctx, &candidates_p);
+        if (token == eos_token) {
+            break;
+        }
+
+        std::string piece = llama_token_to_piece(ctx, token);
+        if (stream) {
+            std::printf("%s", piece.c_str());
+            std::fflush(stdout);
+        }
+
+        inputs.push_back(token);
+
+        result += piece;
+    }
+
+    if (stream) {
+        std::printf("\n");
+    }
+
+    llama_batch_free(bat);
+
+    return result;
+}
+
+static std::string gritlm_instruction(const std::string & instruction) {
+    return !instruction.empty() ? "<|user|>\n" + instruction + "\n<|embed|>\n" : "<|embed|>\n";
+}
+
+int main(int argc, char * argv[]) {
+    gpt_params params;
+    if (!gpt_params_parse(argc, argv, params)) {
+        return 1;
+    }
+
+    llama_model_params mparams = llama_model_params_from_gpt_params(params);
+    llama_context_params cparams = llama_context_params_from_gpt_params(params);
+
+    llama_backend_init();
+
+    llama_model * mdl = llama_load_model_from_file(params.model.c_str(), mparams);
+
+    // create new context - set to embedding mode
+    cparams.embeddings = true;
+    llama_context * ctx = llama_new_context_with_model(mdl, cparams);
+
+    // ### Embedding/Representation ###
+    // samples taken from: https://github.com/ContextualAI/gritlm#basic
+    {
+        const std::string instruction = "Given a scientific paper title, retrieve the paper's abstract";
+
+        const std::vector<std::string> queries = {
+            "Bitcoin: A Peer-to-Peer Electronic Cash System",
+            "Generative Representational Instruction Tuning",
+        };
+
+        const std::vector<std::string> documents = {
+            "A purely peer-to-peer version of electronic cash would allow online payments to be sent directly from one party to another without going through a financial institution. Digital signatures provide part of the solution, but the main benefits are lost if a trusted third party is still required to prevent double-spending. We propose a solution to the double-spending problem using a peer-to-peer network. The network timestamps transactions by hashing them into an ongoing chain of hash-based proof-of-work, forming a record that cannot be changed without redoing the proof-of-work. The longest chain not only serves as proof of the sequence of events witnessed, but proof that it came from the largest pool of CPU power. As long as a majority of CPU power is controlled by nodes that are not cooperating to attack the network, they'll generate the longest chain and outpace attackers. The network itself requires minimal structure. Messages are broadcast on a best effort basis, and nodes can leave and rejoin the network at will, accepting the longest proof-of-work chain as proof of what happened while they were gone.",
+            "All text-based language problems can be reduced to either generation or embedding. Current models only perform well at one or the other. We introduce generative representational instruction tuning (GRIT) whereby a large language model is trained to handle both generative and embedding tasks by distinguishing between them through instructions. Compared to other open models, our resulting GritLM 7B sets a new state of the art on the Massive Text Embedding Benchmark (MTEB) and outperforms all models up to its size on a range of generative tasks. By scaling up further, GritLM 8X7B outperforms all open generative language models that we tried while still being among the best embedding models. Notably, we find that GRIT matches training on only generative or embedding data, thus we can unify both at no performance loss. Among other benefits, the unification via GRIT speeds up Retrieval-Augmented Generation (RAG) by > 60% for long documents, by no longer requiring separate retrieval and generation models. Models, code, etc. are freely available at https://github.com/ContextualAI/gritlm.",
+        };
+
+        // No need to add instruction for retrieval documents
+        const std::vector<std::vector<float>> d_rep = encode(ctx, documents, gritlm_instruction(""));
+        const std::vector<std::vector<float>> q_rep = encode(ctx, queries,   gritlm_instruction(instruction));
+
+        const float cosine_sim_q0_d0 = cosine_similarity(q_rep[0], d_rep[0]);
+        const float cosine_sim_q0_d1 = cosine_similarity(q_rep[0], d_rep[1]);
+        const float cosine_sim_q1_d0 = cosine_similarity(q_rep[1], d_rep[0]);
+        const float cosine_sim_q1_d1 = cosine_similarity(q_rep[1], d_rep[1]);
+
+        std::printf("Cosine similarity between \"%.50s\" and \"%.50s\" is: %.3f\n", queries[0].c_str(), documents[0].c_str(), cosine_sim_q0_d0);
+        std::printf("Cosine similarity between \"%.50s\" and \"%.50s\" is: %.3f\n", queries[0].c_str(), documents[1].c_str(), cosine_sim_q0_d1);
+        std::printf("Cosine similarity between \"%.50s\" and \"%.50s\" is: %.3f\n", queries[1].c_str(), documents[0].c_str(), cosine_sim_q1_d0);
+        std::printf("Cosine similarity between \"%.50s\" and \"%.50s\" is: %.3f\n", queries[1].c_str(), documents[1].c_str(), cosine_sim_q1_d1);
+    }
+
+    // ### Generation ###
+    // GritLM models are not finetuned with system prompts, as you can just include system-like instructions together with your user instruction
+    {
+        const std::string prompt = "<|user|>\nPlease write me a poem about my recent hike of Mt. Fuji at midnight in the style of Shakespeare.\n<|assistant|>\n";
+        std::string response = generate(ctx, prompt, true);
+    }
+
+    llama_free(ctx);
+    llama_free_model(mdl);
+    llama_backend_free();
+
+    return 0;
+}
diff --git a/examples/llama.android/app/src/main/cpp/llama-android.cpp b/examples/llama.android/app/src/main/cpp/llama-android.cpp
index 2beb1e0d5..ce8ab3b70 100644
--- a/examples/llama.android/app/src/main/cpp/llama-android.cpp
+++ b/examples/llama.android/app/src/main/cpp/llama-android.cpp
@@ -33,6 +33,45 @@ jclass la_int_var;
 jmethodID la_int_var_value;
 jmethodID la_int_var_inc;
 
+std::string cached_token_chars;
+
+bool is_valid_utf8(const char * string) {
+    if (!string) {
+        return true;
+    }
+
+    const unsigned char * bytes = (const unsigned char *)string;
+    int num;
+
+    while (*bytes != 0x00) {
+        if ((*bytes & 0x80) == 0x00) {
+            // U+0000 to U+007F
+            num = 1;
+        } else if ((*bytes & 0xE0) == 0xC0) {
+            // U+0080 to U+07FF
+            num = 2;
+        } else if ((*bytes & 0xF0) == 0xE0) {
+            // U+0800 to U+FFFF
+            num = 3;
+        } else if ((*bytes & 0xF8) == 0xF0) {
+            // U+10000 to U+10FFFF
+            num = 4;
+        } else {
+            return false;
+        }
+
+        bytes += 1;
+        for (int i = 1; i < num; ++i) {
+            if ((*bytes & 0xC0) != 0x80) {
+                return false;
+            }
+            bytes += 1;
+        }
+    }
+
+    return true;
+}
+
 static void log_callback(ggml_log_level level, const char * fmt, void * data) {
     if (level == GGML_LOG_LEVEL_ERROR)     __android_log_print(ANDROID_LOG_ERROR, TAG, fmt, data);
     else if (level == GGML_LOG_LEVEL_INFO) __android_log_print(ANDROID_LOG_INFO, TAG, fmt, data);
@@ -295,6 +334,8 @@ Java_com_example_llama_Llm_completion_1init(
         jint n_len
     ) {
 
+    cached_token_chars.clear();
+
     const auto text = env->GetStringUTFChars(jtext, 0);
     const auto context = reinterpret_cast<llama_context *>(context_pointer);
     const auto batch = reinterpret_cast<llama_batch *>(batch_pointer);
@@ -372,8 +413,16 @@ Java_com_example_llama_Llm_completion_1loop(
     }
 
     auto new_token_chars = llama_token_to_piece(context, new_token_id);
-    LOGi("new_token_chars: `%s`", new_token_chars.c_str());
-    auto new_token = env->NewStringUTF(new_token_chars.c_str());
+    cached_token_chars += new_token_chars;
+
+    jstring new_token = nullptr;
+    if (is_valid_utf8(cached_token_chars.c_str())) {
+        new_token = env->NewStringUTF(cached_token_chars.c_str());
+        LOGi("cached: %s, new_token_chars: `%s`, id: %d", cached_token_chars.c_str(), new_token_chars.c_str(), new_token_id);
+        cached_token_chars.clear();
+    } else {
+        new_token = env->NewStringUTF("");
+    }
 
     llama_batch_clear(*batch);
     llama_batch_add(*batch, new_token_id, n_cur, { 0 }, true);
diff --git a/examples/llama.android/app/src/main/java/com/example/llama/Llm.kt b/examples/llama.android/app/src/main/java/com/example/llama/Llm.kt
index 5f3270372..d86afee37 100644
--- a/examples/llama.android/app/src/main/java/com/example/llama/Llm.kt
+++ b/examples/llama.android/app/src/main/java/com/example/llama/Llm.kt
@@ -71,7 +71,7 @@ class Llm {
         batch: Long,
         nLen: Int,
         ncur: IntVar
-    ): String
+    ): String?
 
     private external fun kv_cache_clear(context: Long)
 
@@ -115,7 +115,7 @@ class Llm {
                 val ncur = IntVar(completion_init(state.context, state.batch, message, nlen))
                 while (ncur.value <= nlen) {
                     val str = completion_loop(state.context, state.batch, nlen, ncur)
-                    if (str.isEmpty()) {
+                    if (str == null) {
                         break
                     }
                     emit(str)
diff --git a/examples/llava/clip.cpp b/examples/llava/clip.cpp
index ef9e4ba7a..6653b815d 100644
--- a/examples/llava/clip.cpp
+++ b/examples/llava/clip.cpp
@@ -1862,7 +1862,6 @@ bool clip_model_quantize(const char * fname_inp, const char * fname_out, const i
 
     std::vector<uint8_t> work(512);
     std::vector<float> conv_buf(512);
-    std::vector<int64_t> hist_all(1 << 4, 0);
     size_t total_size_org = 0;
     size_t total_size_new = 0;
 
@@ -1917,48 +1916,7 @@ bool clip_model_quantize(const char * fname_inp, const char * fname_out, const i
             }
             new_data = work.data();
 
-            std::vector<int64_t> hist_cur(1 << 4, 0);
-
-            switch (new_type) {
-                case GGML_TYPE_Q4_0: {
-                    new_size = ggml_quantize_q4_0(f32_data, new_data, n_elms, cur->ne[0], hist_cur.data());
-                } break;
-                case GGML_TYPE_Q4_1: {
-                    new_size = ggml_quantize_q4_1(f32_data, new_data, n_elms, cur->ne[0], hist_cur.data());
-                } break;
-                case GGML_TYPE_Q5_0: {
-                    new_size = ggml_quantize_q5_0(f32_data, new_data, n_elms, cur->ne[0], hist_cur.data());
-                } break;
-                case GGML_TYPE_Q5_1: {
-                    new_size = ggml_quantize_q5_1(f32_data, new_data, n_elms, cur->ne[0], hist_cur.data());
-                } break;
-                case GGML_TYPE_Q8_0: {
-                    new_size = ggml_quantize_q8_0(f32_data, new_data, n_elms, cur->ne[0], hist_cur.data());
-                } break;
-                case GGML_TYPE_Q2_K: {
-                    new_size = ggml_quantize_q2_K(f32_data, new_data, n_elms, cur->ne[0], hist_cur.data());
-                } break;
-                case GGML_TYPE_Q3_K: {
-                    new_size = ggml_quantize_q3_K(f32_data, new_data, n_elms, cur->ne[0], hist_cur.data());
-                } break;
-                case GGML_TYPE_Q4_K: {
-                    new_size = ggml_quantize_q4_K(f32_data, new_data, n_elms, cur->ne[0], hist_cur.data());
-                } break;
-                case GGML_TYPE_Q5_K: {
-                    new_size = ggml_quantize_q5_K(f32_data, new_data, n_elms, cur->ne[0], hist_cur.data());
-                } break;
-                case GGML_TYPE_Q6_K: {
-                    new_size = ggml_quantize_q6_K(f32_data, new_data, n_elms, cur->ne[0], hist_cur.data());
-                } break;
-                default: {
-                    fprintf(stderr, "%s: unsupported quantization type %d\n", __func__, new_type);
-                    return false;
-                }
-            }
-
-            for (size_t j = 0; j < hist_cur.size(); ++j) {
-                hist_all[j] += hist_cur[j];
-            }
+            new_size = ggml_quantize_chunk(new_type, f32_data, new_data, 0, n_elms/cur->ne[0], cur->ne[0], nullptr);
         } else {
             new_type = cur->type;
             new_data = cur->data;
@@ -1993,17 +1951,6 @@ bool clip_model_quantize(const char * fname_inp, const char * fname_out, const i
     {
         printf("%s: original  size = %8.2f MB\n", __func__, total_size_org / 1024.0 / 1024.0);
         printf("%s: quantized size = %8.2f MB\n", __func__, total_size_new / 1024.0 / 1024.0);
-
-        int64_t sum_all = 0;
-        for (size_t i = 0; i < hist_all.size(); ++i) {
-            sum_all += hist_all[i];
-        }
-
-        printf("%s: hist: ", __func__);
-        for (size_t i = 0; i < hist_all.size(); ++i) {
-            printf("%5.3f ", hist_all[i] / (float)sum_all);
-        }
-        printf("\n");
     }
 
     return true;
diff --git a/examples/perplexity/perplexity.cpp b/examples/perplexity/perplexity.cpp
index 02ed6cf0c..1d1048afb 100644
--- a/examples/perplexity/perplexity.cpp
+++ b/examples/perplexity/perplexity.cpp
@@ -443,7 +443,7 @@ static results_perplexity perplexity_v2(llama_context * ctx, const gpt_params &
     return {tokens, std::exp(nll / count), logit_history, prob_history};
 }
 
-static results_perplexity perplexity(llama_context * ctx, const gpt_params & params) {
+static results_perplexity perplexity(llama_context * ctx, const gpt_params & params, const int32_t n_ctx) {
     if (params.ppl_stride > 0) {
         return perplexity_v2(ctx, params);
     }
@@ -454,7 +454,6 @@ static results_perplexity perplexity(llama_context * ctx, const gpt_params & par
     // BOS tokens will be added for each chunk before eval
 
     const bool add_bos = llama_should_add_bos_token(llama_get_model(ctx));
-    const int n_ctx = llama_n_ctx(ctx);
 
     std::ofstream logits_stream;
     if (!params.logits_file.empty()) {
@@ -500,13 +499,19 @@ static results_perplexity perplexity(llama_context * ctx, const gpt_params & par
     double nll2 = 0.0;
 
     const int num_batches = (n_ctx + n_batch - 1) / n_batch;
+    const int n_seq = std::max(1, n_batch / n_ctx);
+
+    GGML_ASSERT(n_batch < n_ctx || n_batch % n_ctx == 0);
+    GGML_ASSERT(params.n_ctx == n_seq * n_ctx);
+
+    llama_batch batch = llama_batch_init(std::min(n_batch, n_ctx*n_seq), 0, 1);
 
     std::vector<float> logits;
     if (num_batches > 1) {
         logits.reserve((size_t)n_ctx * n_vocab);
     }
 
-    fprintf(stderr, "%s: calculating perplexity over %d chunks, batch_size=%d\n", __func__, n_chunk, n_batch);
+    fprintf(stderr, "%s: calculating perplexity over %d chunks, n_ctx=%d, batch_size=%d, n_seq=%d\n", __func__, n_chunk, n_ctx, n_batch, n_seq);
 
     std::vector<std::thread> workers(std::thread::hardware_concurrency() - 1);
 
@@ -519,10 +524,26 @@ static results_perplexity perplexity(llama_context * ctx, const gpt_params & par
         log_probs.resize(n_ctx * nv);
     }
 
-    for (int i = 0; i < n_chunk; ++i) {
+    // We get the logits for all the tokens in the context window (params.n_ctx)
+    // from llama_eval above.  Now, based on https://huggingface.co/docs/transformers/perplexity,
+    // calculate the perplexity over the last half of the window (so the model always has
+    // some context to predict the token).
+    //
+    // We rely on the fact that attention in the forward pass only looks at previous
+    // tokens here, so the logits returned for each token are an accurate representation
+    // of what the model would have predicted at that point.
+    //
+    // Example, we have a context window of 512, we will compute perplexity for each of the
+    // last 256 tokens.  Then, we split the input up into context window size chunks to
+    // process the entire prompt.
+    const int first = n_ctx/2;
+
+    for (int i = 0; i < n_chunk; i += n_seq) {
         const int start =     i * n_ctx;
         const int end   = start + n_ctx;
 
+        const int n_seq_batch = std::min(n_seq, n_chunk - i);
+
         const auto t_start = std::chrono::high_resolution_clock::now();
 
         // clear the KV cache
@@ -532,22 +553,37 @@ static results_perplexity perplexity(llama_context * ctx, const gpt_params & par
             const int batch_start = start + j * n_batch;
             const int batch_size  = std::min(end - batch_start, n_batch);
 
-            // save original token and restore it after eval
-            const auto token_org = tokens[batch_start];
+            batch.n_tokens = 0;
+            for (int seq = 0; seq < n_seq_batch; seq++) {
+                int seq_start = batch_start + seq*n_ctx;
 
-            // add BOS token for the first batch of each chunk
-            if (add_bos && j == 0) {
-                tokens[batch_start] = llama_token_bos(llama_get_model(ctx));
+                // save original token and restore it after eval
+                const auto token_org = tokens[seq_start];
+
+                // add BOS token for the first batch of each chunk
+                if (add_bos && j == 0) {
+                    tokens[seq_start] = llama_token_bos(llama_get_model(ctx));
+                }
+
+                for (int k = 0; k < batch_size; ++k) {
+                    const int idx = seq*n_ctx + k;
+                    batch.token[idx] = tokens[seq_start + k];
+                    batch.pos[idx] = j*n_batch + k;
+                    batch.n_seq_id[idx] = 1;
+                    batch.seq_id[idx][0] = seq;
+                    batch.logits[idx] = batch.pos[idx] >= first ? 1 : 0;
+                }
+                batch.n_tokens += batch_size;
+
+                // restore the original token in case it was set to BOS
+                tokens[seq_start] = token_org;
             }
 
-            if (llama_decode(ctx, llama_batch_get_one(tokens.data() + batch_start, batch_size, j * n_batch, 0))) {
+            if (llama_decode(ctx, batch)) {
                 fprintf(stderr, "%s : failed to eval\n", __func__);
                 return {tokens, -1, logit_history, prob_history};
             }
 
-            // restore the original token in case it was set to BOS
-            tokens[batch_start] = token_org;
-
             if (num_batches > 1) {
                 const auto * batch_logits = llama_get_logits(ctx);
                 logits.insert(logits.end(), batch_logits, batch_logits + batch_size * n_vocab);
@@ -559,7 +595,7 @@ static results_perplexity perplexity(llama_context * ctx, const gpt_params & par
         if (i == 0) {
             const float t_total = std::chrono::duration<float>(t_end - t_start).count();
             fprintf(stderr, "%s: %.2f seconds per pass - ETA ", __func__, t_total);
-            int total_seconds = (int)(t_total * n_chunk);
+            int total_seconds = (int)(t_total*n_chunk/n_seq);
             if (total_seconds >= 60*60) {
                 fprintf(stderr, "%d hours ", total_seconds / (60*60));
                 total_seconds = total_seconds % (60*60);
@@ -567,37 +603,31 @@ static results_perplexity perplexity(llama_context * ctx, const gpt_params & par
             fprintf(stderr, "%.2f minutes\n", total_seconds / 60.0);
         }
 
-        // We get the logits for all the tokens in the context window (params.n_ctx)
-        // from llama_eval above.  Now, based on https://huggingface.co/docs/transformers/perplexity,
-        // calculate the perplexity over the last half of the window (so the model always has
-        // some context to predict the token).
-        //
-        // We rely on the fact that attention in the forward pass only looks at previous
-        // tokens here, so the logits returned for each token are an accurate representation
-        // of what the model would have predicted at that point.
-        //
-        // Example, we have a context window of 512, we will compute perplexity for each of the
-        // last 256 tokens.  Then, we split the input up into context window size chunks to
-        // process the entire prompt.
-        const int first = n_ctx/2;
-        const float * all_logits = num_batches > 1 ? logits.data() : llama_get_logits(ctx);
-        if (!params.logits_file.empty()) {
-            process_logits(logits_stream, n_vocab, all_logits + first*n_vocab, tokens.data() + start + first, n_ctx - 1 - first,
-                    workers, log_probs, nll, nll2);
-        } else {
-            process_logits(n_vocab, all_logits + first*n_vocab, tokens.data() + start + first, n_ctx - 1 - first,
-                    workers, nll, nll2, logit_history.data() + start + first, prob_history.data() + start + first);
-        }
-        count += n_ctx - first - 1;
+        for (int seq = 0; seq < n_seq_batch; seq++) {
+            const float * all_logits = num_batches > 1 ? logits.data() : llama_get_logits_ith(ctx, seq*n_ctx);
+            llama_token * tokens_data = tokens.data() + start + seq*n_ctx + first;
+            if (!params.logits_file.empty()) {
+                process_logits(logits_stream, n_vocab, all_logits + first*n_vocab,
+                        tokens_data, n_ctx - 1 - first,
+                        workers, log_probs, nll, nll2);
+            } else {
+                process_logits(n_vocab, all_logits + first*n_vocab,
+                        tokens_data, n_ctx - 1 - first,
+                        workers, nll, nll2,
+                        logit_history.data() + start + seq*n_ctx + first,
+                        prob_history.data()  + start + seq*n_ctx + first);
+            }
+            count += n_ctx - first - 1;
 
-        // perplexity is e^(average negative log-likelihood)
-        if (params.ppl_output_type == 0) {
-            printf("[%d]%.4lf,", i + 1, std::exp(nll / count));
-        } else {
-            double av = nll/count;
-            double av2 = nll2/count - av*av;
-            if (av2 > 0) av2 = sqrt(av2/(count-1));
-            printf("%8d  %.4lf  %4lf  %4lf\n", i*n_ctx, std::exp(nll / count), av, av2);
+            // perplexity is e^(average negative log-likelihood)
+            if (params.ppl_output_type == 0) {
+                printf("[%d]%.4lf,", i + seq + 1, std::exp(nll / count));
+            } else {
+                double av = nll/count;
+                double av2 = nll2/count - av*av;
+                if (av2 > 0) av2 = sqrt(av2/(count-1));
+                printf("%8d  %.4lf  %4lf  %4lf\n", i*n_ctx, std::exp(nll / count), av, av2);
+            }
         }
         fflush(stdout);
 
@@ -616,6 +646,8 @@ static results_perplexity perplexity(llama_context * ctx, const gpt_params & par
         printf("Unexpected negative standard deviation of log(prob)\n");
     }
 
+    llama_batch_free(batch);
+
     return {tokens, ppl, logit_history, prob_history};
 }
 
@@ -1783,13 +1815,24 @@ static void kl_divergence(llama_context * ctx, const gpt_params & params) {
 int main(int argc, char ** argv) {
     gpt_params params;
 
-    params.n_batch = 512;
     if (!gpt_params_parse(argc, argv, params)) {
         return 1;
     }
 
     params.logits_all = true;
-    params.n_batch = std::min(params.n_batch, params.n_ctx);
+
+    const int32_t n_ctx = params.n_ctx;
+
+    const bool ppl = !params.hellaswag && !params.winogrande && !params.multiple_choice && !params.kl_divergence;
+    if (ppl) {
+        int n_seq = std::max(1, params.n_batch / n_ctx);
+        int32_t n_kv = n_seq * n_ctx;
+        params.n_parallel = n_seq;
+        params.n_ctx = n_kv;
+        params.n_batch = std::min(params.n_batch, n_kv);
+    } else {
+        params.n_batch = std::min(params.n_batch, params.n_ctx);
+    }
 
     if (params.ppl_stride > 0) {
         fprintf(stderr, "Will perform strided perplexity calculation -> adjusting context size from %d to %d\n",
@@ -1848,7 +1891,7 @@ int main(int argc, char ** argv) {
     } else if (params.kl_divergence) {
         kl_divergence(ctx, params);
     } else {
-        results = perplexity(ctx, params);
+        results = perplexity(ctx, params, n_ctx);
     }
 
     llama_print_timings(ctx);
diff --git a/examples/server/CMakeLists.txt b/examples/server/CMakeLists.txt
index c21eba634..f94de1e99 100644
--- a/examples/server/CMakeLists.txt
+++ b/examples/server/CMakeLists.txt
@@ -1,5 +1,6 @@
 set(TARGET server)
 option(LLAMA_SERVER_VERBOSE "Build verbose logging option for Server" ON)
+option(LLAMA_SERVER_SSL "Build SSL support for the server" OFF)
 include_directories(${CMAKE_CURRENT_SOURCE_DIR})
 add_executable(${TARGET} server.cpp utils.hpp json.hpp httplib.h)
 install(TARGETS ${TARGET} RUNTIME)
@@ -7,6 +8,11 @@ target_compile_definitions(${TARGET} PRIVATE
     SERVER_VERBOSE=$<BOOL:${LLAMA_SERVER_VERBOSE}>
 )
 target_link_libraries(${TARGET} PRIVATE common ${CMAKE_THREAD_LIBS_INIT})
+if (LLAMA_SERVER_SSL)
+    find_package(OpenSSL REQUIRED)
+    target_link_libraries(${TARGET} PRIVATE OpenSSL::SSL OpenSSL::Crypto)
+    target_compile_definitions(${TARGET} PRIVATE CPPHTTPLIB_OPENSSL_SUPPORT)
+endif()
 if (WIN32)
     TARGET_LINK_LIBRARIES(${TARGET} PRIVATE ws2_32)
 endif()
diff --git a/examples/server/README.md b/examples/server/README.md
index 591f748f8..8f8454aff 100644
--- a/examples/server/README.md
+++ b/examples/server/README.md
@@ -42,7 +42,7 @@ see https://github.com/ggerganov/llama.cpp/issues/1437
 - `-to N`, `--timeout N`: Server read/write timeout in seconds. Default `600`.
 - `--host`: Set the hostname or ip address to listen. Default `127.0.0.1`.
 - `--port`: Set the port to listen. Default: `8080`.
-- `--path`: path from which to serve static files (default examples/server/public)
+- `--path`: path from which to serve static files (default: disabled)
 - `--api-key`: Set an api key for request authorization. By default the server responds to every request. With an api key set, the requests must have the Authorization header set with the api key as Bearer token. May be used multiple times to enable multiple valid keys.
 - `--api-key-file`: path to file containing api keys delimited by new lines. If set, requests must include one of the keys for access. May be used in conjunction with `--api-key`'s.
 - `--embedding`: Enable embedding extraction, Default: disabled.
@@ -59,6 +59,10 @@ see https://github.com/ggerganov/llama.cpp/issues/1437
 - `--log-disable`: Output logs to stdout only, default: enabled.
 - `--log-format FORMAT`: Define the log output to FORMAT: json or text (default: json)
 
+**If compiled with `LLAMA_SERVER_SSL=ON`**
+- `--ssl-key-file FNAME`: path to file a PEM-encoded SSL private key
+- `--ssl-cert-file FNAME`: path to file a PEM-encoded SSL certificate
+
 ## Build
 
 server is build alongside everything else from the root of the project
@@ -75,6 +79,28 @@ server is build alongside everything else from the root of the project
   cmake --build . --config Release
   ```
 
+## Build with SSL
+
+server can also be built with SSL support using OpenSSL 3
+
+- Using `make`:
+
+  ```bash
+  # NOTE: For non-system openssl, use the following:
+  #   CXXFLAGS="-I /path/to/openssl/include"
+  #   LDFLAGS="-L /path/to/openssl/lib"
+  make LLAMA_SERVER_SSL=true server
+  ```
+
+- Using `CMake`:
+
+  ```bash
+  mkdir build
+  cd build
+  cmake .. -DLLAMA_SERVER_SSL=ON
+  make server
+  ```
+
 ## Quick Start
 
 To get started right away, run the following command, making sure to use the correct path for the model you have:
@@ -97,10 +123,10 @@ You can consume the endpoints with Postman or NodeJS with axios library. You can
 ### Docker
 
 ```bash
-docker run -p 8080:8080 -v /path/to/models:/models ggerganov/llama.cpp:server -m models/7B/ggml-model.gguf -c 512 --host 0.0.0.0 --port 8080
+docker run -p 8080:8080 -v /path/to/models:/models ghcr.io/ggerganov/llama.cpp:server -m models/7B/ggml-model.gguf -c 512 --host 0.0.0.0 --port 8080
 
 # or, with CUDA:
-docker run -p 8080:8080 -v /path/to/models:/models --gpus all ggerganov/llama.cpp:server-cuda -m models/7B/ggml-model.gguf -c 512 --host 0.0.0.0 --port 8080 --n-gpu-layers 99
+docker run -p 8080:8080 -v /path/to/models:/models --gpus all ghcr.io/ggerganov/llama.cpp:server-cuda -m models/7B/ggml-model.gguf -c 512 --host 0.0.0.0 --port 8080 --n-gpu-layers 99
 ```
 
 ## Testing with CURL
@@ -169,7 +195,11 @@ node index.js
 
     *Options:*
 
-    `prompt`: Provide the prompt for this completion as a string or as an array of strings or numbers representing tokens. Internally, the prompt is compared to the previous completion and only the "unseen" suffix is evaluated. If the prompt is a string or an array with the first element given as a string, a `bos` token is inserted in the front like `main` does.
+    `prompt`: Provide the prompt for this completion as a string or as an array of strings or numbers representing tokens. Internally, if `cache_prompt` is `true`, the prompt is compared to the previous completion and only the "unseen" suffix is evaluated. A `BOS` token is inserted at the start, if all of the following conditions are true:
+
+      - The prompt is a string or an array with the first element given as a string
+      - The model's `tokenizer.ggml.add_bos_token` metadata is `true`
+      - The system prompt is empty
 
     `temperature`: Adjust the randomness of the generated text (default: 0.8).
 
@@ -282,7 +312,7 @@ Notice that each `probs` is an array of length `n_probs`.
 
     `content`: Set the text to tokenize.
 
-    Note that the special `BOS` token is not added in front of the text and also a space character is not inserted automatically as it is for `/completion`.
+    Note that a special `BOS` token is never inserted.
 
 - **POST** `/detokenize`: Convert tokens to text.
 
@@ -526,13 +556,55 @@ Run with bash:
 bash chat.sh
 ```
 
-### API like OAI
+### OAI-like API
 
-The HTTP server supports OAI-like API
+The HTTP server supports OAI-like API: https://github.com/openai/openai-openapi
+
+### API errors
+
+Server returns error in the same format as OAI: https://github.com/openai/openai-openapi
+
+Example of an error:
+
+```json
+{
+    "error": {
+        "code": 401,
+        "message": "Invalid API Key",
+        "type": "authentication_error"
+    }
+}
+```
+
+Apart from error types supported by OAI, we also have custom types that are specific to functionalities of llama.cpp:
+
+**When /metrics or /slots endpoint is disabled**
+
+```json
+{
+    "error": {
+        "code": 501,
+        "message": "This server does not support metrics endpoint.",
+        "type": "not_supported_error"
+    }
+}
+```
+
+**When the server receives invalid grammar via */completions endpoint**
+
+```json
+{
+    "error": {
+        "code": 400,
+        "message": "Failed to parse grammar",
+        "type": "invalid_request_error"
+    }
+}
+```
 
 ### Extending or building alternative Web Front End
 
-The default location for the static files is `examples/server/public`. You can extend the front end by running the server binary with `--path` set to `./your-directory` and importing `/completion.js` to get access to the llamaComplete() method.
+You can extend the front end by running the server binary with `--path` set to `./your-directory` and importing `/completion.js` to get access to the llamaComplete() method.
 
 Read the documentation in `/completion.js` to see convenient ways to access llama.
 
diff --git a/examples/server/bench/README.md b/examples/server/bench/README.md
new file mode 100644
index 000000000..a53ad64d7
--- /dev/null
+++ b/examples/server/bench/README.md
@@ -0,0 +1,88 @@
+### Server benchmark tools
+
+Benchmark is using [k6](https://k6.io/).
+
+##### Install k6
+
+Follow instruction from: https://k6.io/docs/get-started/installation/
+
+Example for ubuntu:
+```shell
+snap install k6
+```
+
+#### Download a dataset
+
+This dataset was originally proposed in [vLLM benchmarks](https://github.com/vllm-project/vllm/blob/main/benchmarks/README.md).
+
+```shell
+wget https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/resolve/main/ShareGPT_V3_unfiltered_cleaned_split.json
+```
+
+#### Download a model
+Example for PHI-2
+
+```shell
+../../../scripts/hf.sh --repo ggml-org/models --file phi-2/ggml-model-q4_0.gguf
+```
+
+#### Start the server
+The server must answer OAI Chat completion requests on `http://localhost:8080/v1` or according to the environment variable `SERVER_BENCH_URL`.
+
+Example:
+```shell
+server --host localhost --port 8080 \
+  --model ggml-model-q4_0.gguf \
+  --cont-batching \
+  --metrics \
+  --parallel 8 \
+  --batch-size 512 \
+  --ctx-size 4096 \
+  --log-format text \
+  -ngl 33
+```
+
+#### Run the benchmark
+
+For 500 chat completions request with 8 concurrent users during maximum 10 minutes, run:
+```shell
+k6 run script.js --duration 10m --iterations 500 --vus 8
+```
+
+The benchmark values can be overridden with:
+- `SERVER_BENCH_URL` server url prefix for chat completions, default `http://localhost:8080/v1`
+- `SERVER_BENCH_N_PROMPTS` total prompts to randomly select in the benchmark, default `480`
+- `SERVER_BENCH_MODEL_ALIAS` model alias to pass in the completion request, default `my-model`
+- `SERVER_BENCH_MAX_TOKENS` max tokens to predict, default: `512`
+- `SERVER_BENCH_DATASET` path to the benchmark dataset file
+- `SERVER_BENCH_MAX_PROMPT_TOKENS` maximum prompt tokens to filter out in the dataset: default `1024`
+- `SERVER_BENCH_MAX_CONTEXT` maximum context size of the completions request to filter out in the dataset: prompt + predicted tokens, default `2048`
+
+Note: the local tokenizer is just a string space split, real number of tokens will differ.
+
+Or with [k6 options](https://k6.io/docs/using-k6/k6-options/reference/):
+
+```shell
+SERVER_BENCH_N_PROMPTS=500 k6 run script.js --duration 10m --iterations 500 --vus 8
+```
+
+To [debug http request](https://k6.io/docs/using-k6/http-debugging/) use `--http-debug="full"`.
+
+#### Metrics
+
+Following metrics are available computed from the OAI chat completions response `usage`:
+- `llamacpp_tokens_second` Trend of `usage.total_tokens / request duration`
+- `llamacpp_prompt_tokens` Trend of `usage.prompt_tokens`
+- `llamacpp_prompt_tokens_total_counter` Counter of `usage.prompt_tokens`
+- `llamacpp_completion_tokens` Trend of `usage.completion_tokens`
+- `llamacpp_completion_tokens_total_counter` Counter of `usage.completion_tokens`
+- `llamacpp_completions_truncated_rate` Rate of completions truncated, i.e. if `finish_reason === 'length'`
+- `llamacpp_completions_stop_rate` Rate of completions stopped by the model, i.e. if `finish_reason === 'stop'`
+
+The script will fail if too many completions are truncated, see `llamacpp_completions_truncated_rate`.
+
+K6 metrics might be compared against [server metrics](../README.md), with:
+
+```shell
+curl http://localhost:8080/metrics
+```
diff --git a/examples/server/bench/script.js b/examples/server/bench/script.js
new file mode 100644
index 000000000..a4f5ac5ab
--- /dev/null
+++ b/examples/server/bench/script.js
@@ -0,0 +1,120 @@
+import http from 'k6/http'
+import {check, sleep} from 'k6'
+import {SharedArray} from 'k6/data'
+import {Counter, Rate, Trend} from 'k6/metrics'
+import exec from 'k6/execution';
+
+// Server chat completions prefix
+const server_url = __ENV.SERVER_BENCH_URL ? __ENV.SERVER_BENCH_URL : 'http://localhost:8080/v1'
+
+// Number of total prompts in the dataset - default 10m / 10 seconds/request * number of users
+const n_prompt = __ENV.SERVER_BENCH_N_PROMPTS ? parseInt(__ENV.SERVER_BENCH_N_PROMPTS) : 600 / 10 * 8
+
+// Model name to request
+const model = __ENV.SERVER_BENCH_MODEL_ALIAS ? __ENV.SERVER_BENCH_MODEL_ALIAS : 'my-model'
+
+// Dataset path
+const dataset_path = __ENV.SERVER_BENCH_DATASET ? __ENV.SERVER_BENCH_DATASET : './ShareGPT_V3_unfiltered_cleaned_split.json'
+
+// Max tokens to predict
+const max_tokens = __ENV.SERVER_BENCH_MAX_TOKENS ? parseInt(__ENV.SERVER_BENCH_MAX_TOKENS) : 512
+
+// Max prompt tokens
+const n_prompt_tokens = __ENV.SERVER_BENCH_MAX_PROMPT_TOKENS ? parseInt(__ENV.SERVER_BENCH_MAX_PROMPT_TOKENS) : 1024
+
+// Max slot context
+const n_ctx_slot = __ENV.SERVER_BENCH_MAX_CONTEXT ? parseInt(__ENV.SERVER_BENCH_MAX_CONTEXT) : 2048
+
+export function setup() {
+    console.info(`Benchmark config: server_url=${server_url} n_prompt=${n_prompt} model=${model} dataset_path=${dataset_path} max_tokens=${max_tokens}`)
+}
+
+const data = new SharedArray('conversations', function () {
+    const tokenizer = (message) => message.split(/[\s,'".?]/)
+
+    return JSON.parse(open(dataset_path))
+        // Filter out the conversations with less than 2 turns.
+        .filter(data => data["conversations"].length >= 2)
+        .filter(data => data["conversations"][0]["from"] === "human")
+        .map(data => {
+            return {
+                prompt: data["conversations"][0]["value"],
+                n_prompt_tokens: tokenizer(data["conversations"][0]["value"]).length,
+                n_completion_tokens: tokenizer(data["conversations"][1]["value"]).length,
+            }
+        })
+        // Filter out too short sequences
+        .filter(conv => conv.n_prompt_tokens >= 4 && conv.n_completion_tokens >= 4)
+        // Filter out too long sequences.
+        .filter(conv => conv.n_prompt_tokens <= n_prompt_tokens && conv.n_prompt_tokens + conv.n_completion_tokens <= n_ctx_slot)
+        // Keep only first n prompts
+        .slice(0, n_prompt)
+})
+
+const llamacpp_prompt_tokens = new Trend('llamacpp_prompt_tokens')
+const llamacpp_completion_tokens = new Trend('llamacpp_completion_tokens')
+const llamacpp_tokens_second = new Trend('llamacpp_tokens_second')
+
+const llamacpp_prompt_tokens_total_counter = new Counter('llamacpp_prompt_tokens_total_counter')
+const llamacpp_completion_tokens_total_counter = new Counter('llamacpp_completion_tokens_total_counter')
+
+const llamacpp_completions_truncated_rate = new Rate('llamacpp_completions_truncated_rate')
+const llamacpp_completions_stop_rate = new Rate('llamacpp_completions_stop_rate')
+
+export const options = {
+    thresholds: {
+        llamacpp_completions_truncated_rate: [
+            // more than 80% of truncated input will abort the test
+            {threshold: 'rate < 0.8', abortOnFail: true, delayAbortEval: '1m'},
+        ],
+    },
+    duration: '10m',
+    vus: 8,
+}
+
+export default function () {
+    const conversation = data[exec.scenario.iterationInInstance % data.length]
+    const payload = {
+        "messages": [
+            {
+                "role": "system",
+                "content": "You are ChatGPT, an AI assistant.",
+            },
+            {
+                "role": "user",
+                "content": conversation.prompt,
+            }
+        ],
+        "model": model,
+        "stream": false,
+        "max_tokens": max_tokens
+    }
+
+    const body = JSON.stringify(payload)
+
+    let res = http.post(`${server_url}/chat/completions`, body, {
+        headers: {'Content-Type': 'application/json'},
+        timeout: '300s'
+    })
+
+    check(res, {'success completion': (r) => r.status === 200})
+
+    if (res.status === 200) {
+        const completions = res.json()
+
+        llamacpp_prompt_tokens.add(completions.usage.prompt_tokens)
+        llamacpp_prompt_tokens_total_counter.add(completions.usage.prompt_tokens)
+
+        llamacpp_completion_tokens.add(completions.usage.completion_tokens)
+        llamacpp_completion_tokens_total_counter.add(completions.usage.completion_tokens)
+
+        llamacpp_completions_truncated_rate.add(completions.choices[0].finish_reason === 'length')
+        llamacpp_completions_stop_rate.add(completions.choices[0].finish_reason === 'stop')
+
+        llamacpp_tokens_second.add(completions.usage.total_tokens / res.timings.duration * 1.e3)
+    } else {
+        console.error(`response: ${res.body} request=${payload}`)
+    }
+
+    sleep(0.3)
+}
diff --git a/examples/server/completion.js.hpp b/examples/server/completion.js.hpp
index f5e696e17..10734091e 100644
--- a/examples/server/completion.js.hpp
+++ b/examples/server/completion.js.hpp
@@ -231,255 +231,256 @@ unsigned char completion_js[] = {
   0x20, 0x20, 0x7d, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
   0x20, 0x20, 0x69, 0x66, 0x20, 0x28, 0x72, 0x65, 0x73, 0x75, 0x6c, 0x74,
   0x2e, 0x65, 0x72, 0x72, 0x6f, 0x72, 0x29, 0x20, 0x7b, 0x0a, 0x20, 0x20,
-  0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x72, 0x65,
-  0x73, 0x75, 0x6c, 0x74, 0x2e, 0x65, 0x72, 0x72, 0x6f, 0x72, 0x20, 0x3d,
-  0x20, 0x4a, 0x53, 0x4f, 0x4e, 0x2e, 0x70, 0x61, 0x72, 0x73, 0x65, 0x28,
-  0x72, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x2e, 0x65, 0x72, 0x72, 0x6f, 0x72,
-  0x29, 0x3b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
-  0x20, 0x20, 0x20, 0x69, 0x66, 0x20, 0x28, 0x72, 0x65, 0x73, 0x75, 0x6c,
-  0x74, 0x2e, 0x65, 0x72, 0x72, 0x6f, 0x72, 0x2e, 0x63, 0x6f, 0x6e, 0x74,
-  0x65, 0x6e, 0x74, 0x2e, 0x69, 0x6e, 0x63, 0x6c, 0x75, 0x64, 0x65, 0x73,
-  0x28, 0x27, 0x73, 0x6c, 0x6f, 0x74, 0x20, 0x75, 0x6e, 0x61, 0x76, 0x61,
-  0x69, 0x6c, 0x61, 0x62, 0x6c, 0x65, 0x27, 0x29, 0x29, 0x20, 0x7b, 0x0a,
+  0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x74, 0x72,
+  0x79, 0x20, 0x7b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
+  0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x72, 0x65, 0x73, 0x75, 0x6c, 0x74,
+  0x2e, 0x65, 0x72, 0x72, 0x6f, 0x72, 0x20, 0x3d, 0x20, 0x4a, 0x53, 0x4f,
+  0x4e, 0x2e, 0x70, 0x61, 0x72, 0x73, 0x65, 0x28, 0x72, 0x65, 0x73, 0x75,
+  0x6c, 0x74, 0x2e, 0x65, 0x72, 0x72, 0x6f, 0x72, 0x29, 0x3b, 0x0a, 0x20,
+  0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
+  0x20, 0x69, 0x66, 0x20, 0x28, 0x72, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x2e,
+  0x65, 0x72, 0x72, 0x6f, 0x72, 0x2e, 0x6d, 0x65, 0x73, 0x73, 0x61, 0x67,
+  0x65, 0x2e, 0x69, 0x6e, 0x63, 0x6c, 0x75, 0x64, 0x65, 0x73, 0x28, 0x27,
+  0x73, 0x6c, 0x6f, 0x74, 0x20, 0x75, 0x6e, 0x61, 0x76, 0x61, 0x69, 0x6c,
+  0x61, 0x62, 0x6c, 0x65, 0x27, 0x29, 0x29, 0x20, 0x7b, 0x0a, 0x20, 0x20,
   0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
   0x20, 0x20, 0x2f, 0x2f, 0x20, 0x54, 0x68, 0x72, 0x6f, 0x77, 0x20, 0x61,
   0x6e, 0x20, 0x65, 0x72, 0x72, 0x6f, 0x72, 0x20, 0x74, 0x6f, 0x20, 0x62,
   0x65, 0x20, 0x63, 0x61, 0x75, 0x67, 0x68, 0x74, 0x20, 0x62, 0x79, 0x20,
   0x75, 0x70, 0x73, 0x74, 0x72, 0x65, 0x61, 0x6d, 0x20, 0x63, 0x61, 0x6c,
   0x6c, 0x65, 0x72, 0x73, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
-  0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x74, 0x68, 0x72, 0x6f, 0x77,
-  0x20, 0x6e, 0x65, 0x77, 0x20, 0x45, 0x72, 0x72, 0x6f, 0x72, 0x28, 0x27,
-  0x73, 0x6c, 0x6f, 0x74, 0x20, 0x75, 0x6e, 0x61, 0x76, 0x61, 0x69, 0x6c,
-  0x61, 0x62, 0x6c, 0x65, 0x27, 0x29, 0x3b, 0x0a, 0x20, 0x20, 0x20, 0x20,
-  0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x7d, 0x20, 0x65, 0x6c,
-  0x73, 0x65, 0x20, 0x7b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
-  0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x63, 0x6f, 0x6e, 0x73, 0x6f,
-  0x6c, 0x65, 0x2e, 0x65, 0x72, 0x72, 0x6f, 0x72, 0x28, 0x60, 0x6c, 0x6c,
-  0x61, 0x6d, 0x61, 0x2e, 0x63, 0x70, 0x70, 0x20, 0x65, 0x72, 0x72, 0x6f,
-  0x72, 0x3a, 0x20, 0x24, 0x7b, 0x72, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x2e,
-  0x65, 0x72, 0x72, 0x6f, 0x72, 0x2e, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e,
-  0x74, 0x7d, 0x60, 0x29, 0x3b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
+  0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x74, 0x68, 0x72,
+  0x6f, 0x77, 0x20, 0x6e, 0x65, 0x77, 0x20, 0x45, 0x72, 0x72, 0x6f, 0x72,
+  0x28, 0x27, 0x73, 0x6c, 0x6f, 0x74, 0x20, 0x75, 0x6e, 0x61, 0x76, 0x61,
+  0x69, 0x6c, 0x61, 0x62, 0x6c, 0x65, 0x27, 0x29, 0x3b, 0x0a, 0x20, 0x20,
+  0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
+  0x7d, 0x20, 0x65, 0x6c, 0x73, 0x65, 0x20, 0x7b, 0x0a, 0x20, 0x20, 0x20,
+  0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
+  0x20, 0x63, 0x6f, 0x6e, 0x73, 0x6f, 0x6c, 0x65, 0x2e, 0x65, 0x72, 0x72,
+  0x6f, 0x72, 0x28, 0x60, 0x6c, 0x6c, 0x61, 0x6d, 0x61, 0x2e, 0x63, 0x70,
+  0x70, 0x20, 0x65, 0x72, 0x72, 0x6f, 0x72, 0x20, 0x5b, 0x24, 0x7b, 0x72,
+  0x65, 0x73, 0x75, 0x6c, 0x74, 0x2e, 0x65, 0x72, 0x72, 0x6f, 0x72, 0x2e,
+  0x63, 0x6f, 0x64, 0x65, 0x7d, 0x20, 0x2d, 0x20, 0x24, 0x7b, 0x72, 0x65,
+  0x73, 0x75, 0x6c, 0x74, 0x2e, 0x65, 0x72, 0x72, 0x6f, 0x72, 0x2e, 0x74,
+  0x79, 0x70, 0x65, 0x7d, 0x5d, 0x3a, 0x20, 0x24, 0x7b, 0x72, 0x65, 0x73,
+  0x75, 0x6c, 0x74, 0x2e, 0x65, 0x72, 0x72, 0x6f, 0x72, 0x2e, 0x6d, 0x65,
+  0x73, 0x73, 0x61, 0x67, 0x65, 0x7d, 0x60, 0x29, 0x3b, 0x0a, 0x20, 0x20,
+  0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
+  0x7d, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
+  0x20, 0x20, 0x7d, 0x20, 0x63, 0x61, 0x74, 0x63, 0x68, 0x28, 0x65, 0x29,
+  0x20, 0x7b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
+  0x20, 0x20, 0x20, 0x20, 0x20, 0x63, 0x6f, 0x6e, 0x73, 0x6f, 0x6c, 0x65,
+  0x2e, 0x65, 0x72, 0x72, 0x6f, 0x72, 0x28, 0x60, 0x6c, 0x6c, 0x61, 0x6d,
+  0x61, 0x2e, 0x63, 0x70, 0x70, 0x20, 0x65, 0x72, 0x72, 0x6f, 0x72, 0x20,
+  0x24, 0x7b, 0x72, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x2e, 0x65, 0x72, 0x72,
+  0x6f, 0x72, 0x7d, 0x60, 0x29, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
   0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x7d, 0x0a, 0x20, 0x20, 0x20, 0x20,
   0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x7d, 0x0a, 0x20, 0x20, 0x20, 0x20,
-  0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x69, 0x66, 0x20, 0x28, 0x72, 0x65,
-  0x73, 0x75, 0x6c, 0x74, 0x2e, 0x65, 0x72, 0x72, 0x6f, 0x72, 0x29, 0x20,
-  0x7b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
-  0x20, 0x20, 0x72, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x2e, 0x65, 0x72, 0x72,
-  0x6f, 0x72, 0x20, 0x3d, 0x20, 0x4a, 0x53, 0x4f, 0x4e, 0x2e, 0x70, 0x61,
-  0x72, 0x73, 0x65, 0x28, 0x72, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x2e, 0x65,
-  0x72, 0x72, 0x6f, 0x72, 0x29, 0x3b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20,
-  0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x63, 0x6f, 0x6e, 0x73, 0x6f,
-  0x6c, 0x65, 0x2e, 0x65, 0x72, 0x72, 0x6f, 0x72, 0x28, 0x60, 0x6c, 0x6c,
-  0x61, 0x6d, 0x61, 0x2e, 0x63, 0x70, 0x70, 0x20, 0x65, 0x72, 0x72, 0x6f,
-  0x72, 0x3a, 0x20, 0x24, 0x7b, 0x72, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x2e,
-  0x65, 0x72, 0x72, 0x6f, 0x72, 0x2e, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e,
-  0x74, 0x7d, 0x60, 0x29, 0x3b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
   0x20, 0x20, 0x20, 0x20, 0x7d, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
-  0x20, 0x20, 0x7d, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x7d, 0x0a,
-  0x20, 0x20, 0x20, 0x20, 0x7d, 0x0a, 0x20, 0x20, 0x7d, 0x20, 0x63, 0x61,
-  0x74, 0x63, 0x68, 0x20, 0x28, 0x65, 0x29, 0x20, 0x7b, 0x0a, 0x20, 0x20,
-  0x20, 0x20, 0x69, 0x66, 0x20, 0x28, 0x65, 0x2e, 0x6e, 0x61, 0x6d, 0x65,
-  0x20, 0x21, 0x3d, 0x3d, 0x20, 0x27, 0x41, 0x62, 0x6f, 0x72, 0x74, 0x45,
-  0x72, 0x72, 0x6f, 0x72, 0x27, 0x29, 0x20, 0x7b, 0x0a, 0x20, 0x20, 0x20,
-  0x20, 0x20, 0x20, 0x63, 0x6f, 0x6e, 0x73, 0x6f, 0x6c, 0x65, 0x2e, 0x65,
-  0x72, 0x72, 0x6f, 0x72, 0x28, 0x22, 0x6c, 0x6c, 0x61, 0x6d, 0x61, 0x20,
-  0x65, 0x72, 0x72, 0x6f, 0x72, 0x3a, 0x20, 0x22, 0x2c, 0x20, 0x65, 0x29,
-  0x3b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x7d, 0x0a, 0x20, 0x20, 0x20, 0x20,
-  0x74, 0x68, 0x72, 0x6f, 0x77, 0x20, 0x65, 0x3b, 0x0a, 0x20, 0x20, 0x7d,
-  0x0a, 0x20, 0x20, 0x66, 0x69, 0x6e, 0x61, 0x6c, 0x6c, 0x79, 0x20, 0x7b,
-  0x0a, 0x20, 0x20, 0x20, 0x20, 0x63, 0x6f, 0x6e, 0x74, 0x72, 0x6f, 0x6c,
-  0x6c, 0x65, 0x72, 0x2e, 0x61, 0x62, 0x6f, 0x72, 0x74, 0x28, 0x29, 0x3b,
-  0x0a, 0x20, 0x20, 0x7d, 0x0a, 0x0a, 0x20, 0x20, 0x72, 0x65, 0x74, 0x75,
-  0x72, 0x6e, 0x20, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x3b, 0x0a,
-  0x7d, 0x0a, 0x0a, 0x2f, 0x2f, 0x20, 0x43, 0x61, 0x6c, 0x6c, 0x20, 0x6c,
-  0x6c, 0x61, 0x6d, 0x61, 0x2c, 0x20, 0x72, 0x65, 0x74, 0x75, 0x72, 0x6e,
-  0x20, 0x61, 0x6e, 0x20, 0x65, 0x76, 0x65, 0x6e, 0x74, 0x20, 0x74, 0x61,
-  0x72, 0x67, 0x65, 0x74, 0x20, 0x74, 0x68, 0x61, 0x74, 0x20, 0x79, 0x6f,
-  0x75, 0x20, 0x63, 0x61, 0x6e, 0x20, 0x73, 0x75, 0x62, 0x73, 0x63, 0x72,
-  0x69, 0x62, 0x65, 0x20, 0x74, 0x6f, 0x0a, 0x2f, 0x2f, 0x0a, 0x2f, 0x2f,
-  0x20, 0x45, 0x78, 0x61, 0x6d, 0x70, 0x6c, 0x65, 0x3a, 0x0a, 0x2f, 0x2f,
-  0x0a, 0x2f, 0x2f, 0x20, 0x20, 0x20, 0x20, 0x69, 0x6d, 0x70, 0x6f, 0x72,
-  0x74, 0x20, 0x7b, 0x20, 0x6c, 0x6c, 0x61, 0x6d, 0x61, 0x45, 0x76, 0x65,
-  0x6e, 0x74, 0x54, 0x61, 0x72, 0x67, 0x65, 0x74, 0x20, 0x7d, 0x20, 0x66,
-  0x72, 0x6f, 0x6d, 0x20, 0x27, 0x2f, 0x63, 0x6f, 0x6d, 0x70, 0x6c, 0x65,
-  0x74, 0x69, 0x6f, 0x6e, 0x2e, 0x6a, 0x73, 0x27, 0x0a, 0x2f, 0x2f, 0x0a,
-  0x2f, 0x2f, 0x20, 0x20, 0x20, 0x20, 0x63, 0x6f, 0x6e, 0x73, 0x74, 0x20,
-  0x63, 0x6f, 0x6e, 0x6e, 0x20, 0x3d, 0x20, 0x6c, 0x6c, 0x61, 0x6d, 0x61,
-  0x45, 0x76, 0x65, 0x6e, 0x74, 0x54, 0x61, 0x72, 0x67, 0x65, 0x74, 0x28,
-  0x70, 0x72, 0x6f, 0x6d, 0x70, 0x74, 0x29, 0x0a, 0x2f, 0x2f, 0x20, 0x20,
-  0x20, 0x20, 0x63, 0x6f, 0x6e, 0x6e, 0x2e, 0x61, 0x64, 0x64, 0x45, 0x76,
-  0x65, 0x6e, 0x74, 0x4c, 0x69, 0x73, 0x74, 0x65, 0x6e, 0x65, 0x72, 0x28,
-  0x22, 0x6d, 0x65, 0x73, 0x73, 0x61, 0x67, 0x65, 0x22, 0x2c, 0x20, 0x28,
-  0x63, 0x68, 0x75, 0x6e, 0x6b, 0x29, 0x20, 0x3d, 0x3e, 0x20, 0x7b, 0x0a,
-  0x2f, 0x2f, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x64, 0x6f, 0x63, 0x75,
-  0x6d, 0x65, 0x6e, 0x74, 0x2e, 0x77, 0x72, 0x69, 0x74, 0x65, 0x28, 0x63,
-  0x68, 0x75, 0x6e, 0x6b, 0x2e, 0x64, 0x65, 0x74, 0x61, 0x69, 0x6c, 0x2e,
-  0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x29, 0x0a, 0x2f, 0x2f, 0x20,
-  0x20, 0x20, 0x20, 0x7d, 0x29, 0x0a, 0x2f, 0x2f, 0x0a, 0x65, 0x78, 0x70,
-  0x6f, 0x72, 0x74, 0x20, 0x63, 0x6f, 0x6e, 0x73, 0x74, 0x20, 0x6c, 0x6c,
-  0x61, 0x6d, 0x61, 0x45, 0x76, 0x65, 0x6e, 0x74, 0x54, 0x61, 0x72, 0x67,
-  0x65, 0x74, 0x20, 0x3d, 0x20, 0x28, 0x70, 0x72, 0x6f, 0x6d, 0x70, 0x74,
-  0x2c, 0x20, 0x70, 0x61, 0x72, 0x61, 0x6d, 0x73, 0x20, 0x3d, 0x20, 0x7b,
-  0x7d, 0x2c, 0x20, 0x63, 0x6f, 0x6e, 0x66, 0x69, 0x67, 0x20, 0x3d, 0x20,
-  0x7b, 0x7d, 0x29, 0x20, 0x3d, 0x3e, 0x20, 0x7b, 0x0a, 0x20, 0x20, 0x63,
-  0x6f, 0x6e, 0x73, 0x74, 0x20, 0x65, 0x76, 0x65, 0x6e, 0x74, 0x54, 0x61,
-  0x72, 0x67, 0x65, 0x74, 0x20, 0x3d, 0x20, 0x6e, 0x65, 0x77, 0x20, 0x45,
-  0x76, 0x65, 0x6e, 0x74, 0x54, 0x61, 0x72, 0x67, 0x65, 0x74, 0x28, 0x29,
-  0x3b, 0x0a, 0x20, 0x20, 0x28, 0x61, 0x73, 0x79, 0x6e, 0x63, 0x20, 0x28,
-  0x29, 0x20, 0x3d, 0x3e, 0x20, 0x7b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x6c,
-  0x65, 0x74, 0x20, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x20, 0x3d,
-  0x20, 0x22, 0x22, 0x3b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x66, 0x6f, 0x72,
-  0x20, 0x61, 0x77, 0x61, 0x69, 0x74, 0x20, 0x28, 0x63, 0x6f, 0x6e, 0x73,
-  0x74, 0x20, 0x63, 0x68, 0x75, 0x6e, 0x6b, 0x20, 0x6f, 0x66, 0x20, 0x6c,
-  0x6c, 0x61, 0x6d, 0x61, 0x28, 0x70, 0x72, 0x6f, 0x6d, 0x70, 0x74, 0x2c,
-  0x20, 0x70, 0x61, 0x72, 0x61, 0x6d, 0x73, 0x2c, 0x20, 0x63, 0x6f, 0x6e,
-  0x66, 0x69, 0x67, 0x29, 0x29, 0x20, 0x7b, 0x0a, 0x20, 0x20, 0x20, 0x20,
-  0x20, 0x20, 0x69, 0x66, 0x20, 0x28, 0x63, 0x68, 0x75, 0x6e, 0x6b, 0x2e,
-  0x64, 0x61, 0x74, 0x61, 0x29, 0x20, 0x7b, 0x0a, 0x20, 0x20, 0x20, 0x20,
-  0x20, 0x20, 0x20, 0x20, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x20,
-  0x2b, 0x3d, 0x20, 0x63, 0x68, 0x75, 0x6e, 0x6b, 0x2e, 0x64, 0x61, 0x74,
-  0x61, 0x2e, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x3b, 0x0a, 0x20,
+  0x7d, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x7d, 0x0a, 0x20, 0x20, 0x7d, 0x20,
+  0x63, 0x61, 0x74, 0x63, 0x68, 0x20, 0x28, 0x65, 0x29, 0x20, 0x7b, 0x0a,
+  0x20, 0x20, 0x20, 0x20, 0x69, 0x66, 0x20, 0x28, 0x65, 0x2e, 0x6e, 0x61,
+  0x6d, 0x65, 0x20, 0x21, 0x3d, 0x3d, 0x20, 0x27, 0x41, 0x62, 0x6f, 0x72,
+  0x74, 0x45, 0x72, 0x72, 0x6f, 0x72, 0x27, 0x29, 0x20, 0x7b, 0x0a, 0x20,
+  0x20, 0x20, 0x20, 0x20, 0x20, 0x63, 0x6f, 0x6e, 0x73, 0x6f, 0x6c, 0x65,
+  0x2e, 0x65, 0x72, 0x72, 0x6f, 0x72, 0x28, 0x22, 0x6c, 0x6c, 0x61, 0x6d,
+  0x61, 0x20, 0x65, 0x72, 0x72, 0x6f, 0x72, 0x3a, 0x20, 0x22, 0x2c, 0x20,
+  0x65, 0x29, 0x3b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x7d, 0x0a, 0x20, 0x20,
+  0x20, 0x20, 0x74, 0x68, 0x72, 0x6f, 0x77, 0x20, 0x65, 0x3b, 0x0a, 0x20,
+  0x20, 0x7d, 0x0a, 0x20, 0x20, 0x66, 0x69, 0x6e, 0x61, 0x6c, 0x6c, 0x79,
+  0x20, 0x7b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x63, 0x6f, 0x6e, 0x74, 0x72,
+  0x6f, 0x6c, 0x6c, 0x65, 0x72, 0x2e, 0x61, 0x62, 0x6f, 0x72, 0x74, 0x28,
+  0x29, 0x3b, 0x0a, 0x20, 0x20, 0x7d, 0x0a, 0x0a, 0x20, 0x20, 0x72, 0x65,
+  0x74, 0x75, 0x72, 0x6e, 0x20, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74,
+  0x3b, 0x0a, 0x7d, 0x0a, 0x0a, 0x2f, 0x2f, 0x20, 0x43, 0x61, 0x6c, 0x6c,
+  0x20, 0x6c, 0x6c, 0x61, 0x6d, 0x61, 0x2c, 0x20, 0x72, 0x65, 0x74, 0x75,
+  0x72, 0x6e, 0x20, 0x61, 0x6e, 0x20, 0x65, 0x76, 0x65, 0x6e, 0x74, 0x20,
+  0x74, 0x61, 0x72, 0x67, 0x65, 0x74, 0x20, 0x74, 0x68, 0x61, 0x74, 0x20,
+  0x79, 0x6f, 0x75, 0x20, 0x63, 0x61, 0x6e, 0x20, 0x73, 0x75, 0x62, 0x73,
+  0x63, 0x72, 0x69, 0x62, 0x65, 0x20, 0x74, 0x6f, 0x0a, 0x2f, 0x2f, 0x0a,
+  0x2f, 0x2f, 0x20, 0x45, 0x78, 0x61, 0x6d, 0x70, 0x6c, 0x65, 0x3a, 0x0a,
+  0x2f, 0x2f, 0x0a, 0x2f, 0x2f, 0x20, 0x20, 0x20, 0x20, 0x69, 0x6d, 0x70,
+  0x6f, 0x72, 0x74, 0x20, 0x7b, 0x20, 0x6c, 0x6c, 0x61, 0x6d, 0x61, 0x45,
+  0x76, 0x65, 0x6e, 0x74, 0x54, 0x61, 0x72, 0x67, 0x65, 0x74, 0x20, 0x7d,
+  0x20, 0x66, 0x72, 0x6f, 0x6d, 0x20, 0x27, 0x2f, 0x63, 0x6f, 0x6d, 0x70,
+  0x6c, 0x65, 0x74, 0x69, 0x6f, 0x6e, 0x2e, 0x6a, 0x73, 0x27, 0x0a, 0x2f,
+  0x2f, 0x0a, 0x2f, 0x2f, 0x20, 0x20, 0x20, 0x20, 0x63, 0x6f, 0x6e, 0x73,
+  0x74, 0x20, 0x63, 0x6f, 0x6e, 0x6e, 0x20, 0x3d, 0x20, 0x6c, 0x6c, 0x61,
+  0x6d, 0x61, 0x45, 0x76, 0x65, 0x6e, 0x74, 0x54, 0x61, 0x72, 0x67, 0x65,
+  0x74, 0x28, 0x70, 0x72, 0x6f, 0x6d, 0x70, 0x74, 0x29, 0x0a, 0x2f, 0x2f,
+  0x20, 0x20, 0x20, 0x20, 0x63, 0x6f, 0x6e, 0x6e, 0x2e, 0x61, 0x64, 0x64,
+  0x45, 0x76, 0x65, 0x6e, 0x74, 0x4c, 0x69, 0x73, 0x74, 0x65, 0x6e, 0x65,
+  0x72, 0x28, 0x22, 0x6d, 0x65, 0x73, 0x73, 0x61, 0x67, 0x65, 0x22, 0x2c,
+  0x20, 0x28, 0x63, 0x68, 0x75, 0x6e, 0x6b, 0x29, 0x20, 0x3d, 0x3e, 0x20,
+  0x7b, 0x0a, 0x2f, 0x2f, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x64, 0x6f,
+  0x63, 0x75, 0x6d, 0x65, 0x6e, 0x74, 0x2e, 0x77, 0x72, 0x69, 0x74, 0x65,
+  0x28, 0x63, 0x68, 0x75, 0x6e, 0x6b, 0x2e, 0x64, 0x65, 0x74, 0x61, 0x69,
+  0x6c, 0x2e, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x29, 0x0a, 0x2f,
+  0x2f, 0x20, 0x20, 0x20, 0x20, 0x7d, 0x29, 0x0a, 0x2f, 0x2f, 0x0a, 0x65,
+  0x78, 0x70, 0x6f, 0x72, 0x74, 0x20, 0x63, 0x6f, 0x6e, 0x73, 0x74, 0x20,
+  0x6c, 0x6c, 0x61, 0x6d, 0x61, 0x45, 0x76, 0x65, 0x6e, 0x74, 0x54, 0x61,
+  0x72, 0x67, 0x65, 0x74, 0x20, 0x3d, 0x20, 0x28, 0x70, 0x72, 0x6f, 0x6d,
+  0x70, 0x74, 0x2c, 0x20, 0x70, 0x61, 0x72, 0x61, 0x6d, 0x73, 0x20, 0x3d,
+  0x20, 0x7b, 0x7d, 0x2c, 0x20, 0x63, 0x6f, 0x6e, 0x66, 0x69, 0x67, 0x20,
+  0x3d, 0x20, 0x7b, 0x7d, 0x29, 0x20, 0x3d, 0x3e, 0x20, 0x7b, 0x0a, 0x20,
+  0x20, 0x63, 0x6f, 0x6e, 0x73, 0x74, 0x20, 0x65, 0x76, 0x65, 0x6e, 0x74,
+  0x54, 0x61, 0x72, 0x67, 0x65, 0x74, 0x20, 0x3d, 0x20, 0x6e, 0x65, 0x77,
+  0x20, 0x45, 0x76, 0x65, 0x6e, 0x74, 0x54, 0x61, 0x72, 0x67, 0x65, 0x74,
+  0x28, 0x29, 0x3b, 0x0a, 0x20, 0x20, 0x28, 0x61, 0x73, 0x79, 0x6e, 0x63,
+  0x20, 0x28, 0x29, 0x20, 0x3d, 0x3e, 0x20, 0x7b, 0x0a, 0x20, 0x20, 0x20,
+  0x20, 0x6c, 0x65, 0x74, 0x20, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74,
+  0x20, 0x3d, 0x20, 0x22, 0x22, 0x3b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x66,
+  0x6f, 0x72, 0x20, 0x61, 0x77, 0x61, 0x69, 0x74, 0x20, 0x28, 0x63, 0x6f,
+  0x6e, 0x73, 0x74, 0x20, 0x63, 0x68, 0x75, 0x6e, 0x6b, 0x20, 0x6f, 0x66,
+  0x20, 0x6c, 0x6c, 0x61, 0x6d, 0x61, 0x28, 0x70, 0x72, 0x6f, 0x6d, 0x70,
+  0x74, 0x2c, 0x20, 0x70, 0x61, 0x72, 0x61, 0x6d, 0x73, 0x2c, 0x20, 0x63,
+  0x6f, 0x6e, 0x66, 0x69, 0x67, 0x29, 0x29, 0x20, 0x7b, 0x0a, 0x20, 0x20,
+  0x20, 0x20, 0x20, 0x20, 0x69, 0x66, 0x20, 0x28, 0x63, 0x68, 0x75, 0x6e,
+  0x6b, 0x2e, 0x64, 0x61, 0x74, 0x61, 0x29, 0x20, 0x7b, 0x0a, 0x20, 0x20,
+  0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e,
+  0x74, 0x20, 0x2b, 0x3d, 0x20, 0x63, 0x68, 0x75, 0x6e, 0x6b, 0x2e, 0x64,
+  0x61, 0x74, 0x61, 0x2e, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x3b,
+  0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x65, 0x76, 0x65,
+  0x6e, 0x74, 0x54, 0x61, 0x72, 0x67, 0x65, 0x74, 0x2e, 0x64, 0x69, 0x73,
+  0x70, 0x61, 0x74, 0x63, 0x68, 0x45, 0x76, 0x65, 0x6e, 0x74, 0x28, 0x6e,
+  0x65, 0x77, 0x20, 0x43, 0x75, 0x73, 0x74, 0x6f, 0x6d, 0x45, 0x76, 0x65,
+  0x6e, 0x74, 0x28, 0x22, 0x6d, 0x65, 0x73, 0x73, 0x61, 0x67, 0x65, 0x22,
+  0x2c, 0x20, 0x7b, 0x20, 0x64, 0x65, 0x74, 0x61, 0x69, 0x6c, 0x3a, 0x20,
+  0x63, 0x68, 0x75, 0x6e, 0x6b, 0x2e, 0x64, 0x61, 0x74, 0x61, 0x20, 0x7d,
+  0x29, 0x29, 0x3b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x7d, 0x0a,
+  0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x69, 0x66, 0x20, 0x28, 0x63, 0x68,
+  0x75, 0x6e, 0x6b, 0x2e, 0x64, 0x61, 0x74, 0x61, 0x2e, 0x67, 0x65, 0x6e,
+  0x65, 0x72, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x5f, 0x73, 0x65, 0x74, 0x74,
+  0x69, 0x6e, 0x67, 0x73, 0x29, 0x20, 0x7b, 0x0a, 0x20, 0x20, 0x20, 0x20,
+  0x20, 0x20, 0x20, 0x20, 0x65, 0x76, 0x65, 0x6e, 0x74, 0x54, 0x61, 0x72,
+  0x67, 0x65, 0x74, 0x2e, 0x64, 0x69, 0x73, 0x70, 0x61, 0x74, 0x63, 0x68,
+  0x45, 0x76, 0x65, 0x6e, 0x74, 0x28, 0x6e, 0x65, 0x77, 0x20, 0x43, 0x75,
+  0x73, 0x74, 0x6f, 0x6d, 0x45, 0x76, 0x65, 0x6e, 0x74, 0x28, 0x22, 0x67,
+  0x65, 0x6e, 0x65, 0x72, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x5f, 0x73, 0x65,
+  0x74, 0x74, 0x69, 0x6e, 0x67, 0x73, 0x22, 0x2c, 0x20, 0x7b, 0x20, 0x64,
+  0x65, 0x74, 0x61, 0x69, 0x6c, 0x3a, 0x20, 0x63, 0x68, 0x75, 0x6e, 0x6b,
+  0x2e, 0x64, 0x61, 0x74, 0x61, 0x2e, 0x67, 0x65, 0x6e, 0x65, 0x72, 0x61,
+  0x74, 0x69, 0x6f, 0x6e, 0x5f, 0x73, 0x65, 0x74, 0x74, 0x69, 0x6e, 0x67,
+  0x73, 0x20, 0x7d, 0x29, 0x29, 0x3b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20,
+  0x20, 0x7d, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x69, 0x66, 0x20,
+  0x28, 0x63, 0x68, 0x75, 0x6e, 0x6b, 0x2e, 0x64, 0x61, 0x74, 0x61, 0x2e,
+  0x74, 0x69, 0x6d, 0x69, 0x6e, 0x67, 0x73, 0x29, 0x20, 0x7b, 0x0a, 0x20,
   0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x65, 0x76, 0x65, 0x6e, 0x74,
   0x54, 0x61, 0x72, 0x67, 0x65, 0x74, 0x2e, 0x64, 0x69, 0x73, 0x70, 0x61,
   0x74, 0x63, 0x68, 0x45, 0x76, 0x65, 0x6e, 0x74, 0x28, 0x6e, 0x65, 0x77,
   0x20, 0x43, 0x75, 0x73, 0x74, 0x6f, 0x6d, 0x45, 0x76, 0x65, 0x6e, 0x74,
-  0x28, 0x22, 0x6d, 0x65, 0x73, 0x73, 0x61, 0x67, 0x65, 0x22, 0x2c, 0x20,
+  0x28, 0x22, 0x74, 0x69, 0x6d, 0x69, 0x6e, 0x67, 0x73, 0x22, 0x2c, 0x20,
   0x7b, 0x20, 0x64, 0x65, 0x74, 0x61, 0x69, 0x6c, 0x3a, 0x20, 0x63, 0x68,
-  0x75, 0x6e, 0x6b, 0x2e, 0x64, 0x61, 0x74, 0x61, 0x20, 0x7d, 0x29, 0x29,
-  0x3b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x7d, 0x0a, 0x20, 0x20,
-  0x20, 0x20, 0x20, 0x20, 0x69, 0x66, 0x20, 0x28, 0x63, 0x68, 0x75, 0x6e,
-  0x6b, 0x2e, 0x64, 0x61, 0x74, 0x61, 0x2e, 0x67, 0x65, 0x6e, 0x65, 0x72,
-  0x61, 0x74, 0x69, 0x6f, 0x6e, 0x5f, 0x73, 0x65, 0x74, 0x74, 0x69, 0x6e,
-  0x67, 0x73, 0x29, 0x20, 0x7b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
-  0x20, 0x20, 0x65, 0x76, 0x65, 0x6e, 0x74, 0x54, 0x61, 0x72, 0x67, 0x65,
-  0x74, 0x2e, 0x64, 0x69, 0x73, 0x70, 0x61, 0x74, 0x63, 0x68, 0x45, 0x76,
-  0x65, 0x6e, 0x74, 0x28, 0x6e, 0x65, 0x77, 0x20, 0x43, 0x75, 0x73, 0x74,
-  0x6f, 0x6d, 0x45, 0x76, 0x65, 0x6e, 0x74, 0x28, 0x22, 0x67, 0x65, 0x6e,
-  0x65, 0x72, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x5f, 0x73, 0x65, 0x74, 0x74,
-  0x69, 0x6e, 0x67, 0x73, 0x22, 0x2c, 0x20, 0x7b, 0x20, 0x64, 0x65, 0x74,
-  0x61, 0x69, 0x6c, 0x3a, 0x20, 0x63, 0x68, 0x75, 0x6e, 0x6b, 0x2e, 0x64,
-  0x61, 0x74, 0x61, 0x2e, 0x67, 0x65, 0x6e, 0x65, 0x72, 0x61, 0x74, 0x69,
-  0x6f, 0x6e, 0x5f, 0x73, 0x65, 0x74, 0x74, 0x69, 0x6e, 0x67, 0x73, 0x20,
-  0x7d, 0x29, 0x29, 0x3b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x7d,
-  0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x69, 0x66, 0x20, 0x28, 0x63,
-  0x68, 0x75, 0x6e, 0x6b, 0x2e, 0x64, 0x61, 0x74, 0x61, 0x2e, 0x74, 0x69,
-  0x6d, 0x69, 0x6e, 0x67, 0x73, 0x29, 0x20, 0x7b, 0x0a, 0x20, 0x20, 0x20,
-  0x20, 0x20, 0x20, 0x20, 0x20, 0x65, 0x76, 0x65, 0x6e, 0x74, 0x54, 0x61,
-  0x72, 0x67, 0x65, 0x74, 0x2e, 0x64, 0x69, 0x73, 0x70, 0x61, 0x74, 0x63,
-  0x68, 0x45, 0x76, 0x65, 0x6e, 0x74, 0x28, 0x6e, 0x65, 0x77, 0x20, 0x43,
-  0x75, 0x73, 0x74, 0x6f, 0x6d, 0x45, 0x76, 0x65, 0x6e, 0x74, 0x28, 0x22,
-  0x74, 0x69, 0x6d, 0x69, 0x6e, 0x67, 0x73, 0x22, 0x2c, 0x20, 0x7b, 0x20,
-  0x64, 0x65, 0x74, 0x61, 0x69, 0x6c, 0x3a, 0x20, 0x63, 0x68, 0x75, 0x6e,
-  0x6b, 0x2e, 0x64, 0x61, 0x74, 0x61, 0x2e, 0x74, 0x69, 0x6d, 0x69, 0x6e,
-  0x67, 0x73, 0x20, 0x7d, 0x29, 0x29, 0x3b, 0x0a, 0x20, 0x20, 0x20, 0x20,
-  0x20, 0x20, 0x7d, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x7d, 0x0a, 0x20, 0x20,
-  0x20, 0x20, 0x65, 0x76, 0x65, 0x6e, 0x74, 0x54, 0x61, 0x72, 0x67, 0x65,
-  0x74, 0x2e, 0x64, 0x69, 0x73, 0x70, 0x61, 0x74, 0x63, 0x68, 0x45, 0x76,
-  0x65, 0x6e, 0x74, 0x28, 0x6e, 0x65, 0x77, 0x20, 0x43, 0x75, 0x73, 0x74,
-  0x6f, 0x6d, 0x45, 0x76, 0x65, 0x6e, 0x74, 0x28, 0x22, 0x64, 0x6f, 0x6e,
-  0x65, 0x22, 0x2c, 0x20, 0x7b, 0x20, 0x64, 0x65, 0x74, 0x61, 0x69, 0x6c,
-  0x3a, 0x20, 0x7b, 0x20, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x20,
-  0x7d, 0x20, 0x7d, 0x29, 0x29, 0x3b, 0x0a, 0x20, 0x20, 0x7d, 0x29, 0x28,
-  0x29, 0x3b, 0x0a, 0x20, 0x20, 0x72, 0x65, 0x74, 0x75, 0x72, 0x6e, 0x20,
-  0x65, 0x76, 0x65, 0x6e, 0x74, 0x54, 0x61, 0x72, 0x67, 0x65, 0x74, 0x3b,
-  0x0a, 0x7d, 0x0a, 0x0a, 0x2f, 0x2f, 0x20, 0x43, 0x61, 0x6c, 0x6c, 0x20,
-  0x6c, 0x6c, 0x61, 0x6d, 0x61, 0x2c, 0x20, 0x72, 0x65, 0x74, 0x75, 0x72,
-  0x6e, 0x20, 0x61, 0x20, 0x70, 0x72, 0x6f, 0x6d, 0x69, 0x73, 0x65, 0x20,
-  0x74, 0x68, 0x61, 0x74, 0x20, 0x72, 0x65, 0x73, 0x6f, 0x6c, 0x76, 0x65,
-  0x73, 0x20, 0x74, 0x6f, 0x20, 0x74, 0x68, 0x65, 0x20, 0x63, 0x6f, 0x6d,
-  0x70, 0x6c, 0x65, 0x74, 0x65, 0x64, 0x20, 0x74, 0x65, 0x78, 0x74, 0x2e,
-  0x20, 0x54, 0x68, 0x69, 0x73, 0x20, 0x64, 0x6f, 0x65, 0x73, 0x20, 0x6e,
-  0x6f, 0x74, 0x20, 0x73, 0x75, 0x70, 0x70, 0x6f, 0x72, 0x74, 0x20, 0x73,
-  0x74, 0x72, 0x65, 0x61, 0x6d, 0x69, 0x6e, 0x67, 0x0a, 0x2f, 0x2f, 0x0a,
-  0x2f, 0x2f, 0x20, 0x45, 0x78, 0x61, 0x6d, 0x70, 0x6c, 0x65, 0x3a, 0x0a,
-  0x2f, 0x2f, 0x0a, 0x2f, 0x2f, 0x20, 0x20, 0x20, 0x20, 0x20, 0x6c, 0x6c,
-  0x61, 0x6d, 0x61, 0x50, 0x72, 0x6f, 0x6d, 0x69, 0x73, 0x65, 0x28, 0x70,
-  0x72, 0x6f, 0x6d, 0x70, 0x74, 0x29, 0x2e, 0x74, 0x68, 0x65, 0x6e, 0x28,
-  0x28, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x29, 0x20, 0x3d, 0x3e,
-  0x20, 0x7b, 0x0a, 0x2f, 0x2f, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
-  0x64, 0x6f, 0x63, 0x75, 0x6d, 0x65, 0x6e, 0x74, 0x2e, 0x77, 0x72, 0x69,
-  0x74, 0x65, 0x28, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x29, 0x0a,
-  0x2f, 0x2f, 0x20, 0x20, 0x20, 0x20, 0x20, 0x7d, 0x29, 0x0a, 0x2f, 0x2f,
-  0x0a, 0x2f, 0x2f, 0x20, 0x20, 0x20, 0x20, 0x20, 0x6f, 0x72, 0x0a, 0x2f,
-  0x2f, 0x0a, 0x2f, 0x2f, 0x20, 0x20, 0x20, 0x20, 0x20, 0x63, 0x6f, 0x6e,
-  0x73, 0x74, 0x20, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x20, 0x3d,
-  0x20, 0x61, 0x77, 0x61, 0x69, 0x74, 0x20, 0x6c, 0x6c, 0x61, 0x6d, 0x61,
-  0x50, 0x72, 0x6f, 0x6d, 0x69, 0x73, 0x65, 0x28, 0x70, 0x72, 0x6f, 0x6d,
-  0x70, 0x74, 0x29, 0x0a, 0x2f, 0x2f, 0x20, 0x20, 0x20, 0x20, 0x20, 0x64,
-  0x6f, 0x63, 0x75, 0x6d, 0x65, 0x6e, 0x74, 0x2e, 0x77, 0x72, 0x69, 0x74,
-  0x65, 0x28, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x29, 0x0a, 0x2f,
-  0x2f, 0x0a, 0x65, 0x78, 0x70, 0x6f, 0x72, 0x74, 0x20, 0x63, 0x6f, 0x6e,
-  0x73, 0x74, 0x20, 0x6c, 0x6c, 0x61, 0x6d, 0x61, 0x50, 0x72, 0x6f, 0x6d,
-  0x69, 0x73, 0x65, 0x20, 0x3d, 0x20, 0x28, 0x70, 0x72, 0x6f, 0x6d, 0x70,
-  0x74, 0x2c, 0x20, 0x70, 0x61, 0x72, 0x61, 0x6d, 0x73, 0x20, 0x3d, 0x20,
-  0x7b, 0x7d, 0x2c, 0x20, 0x63, 0x6f, 0x6e, 0x66, 0x69, 0x67, 0x20, 0x3d,
-  0x20, 0x7b, 0x7d, 0x29, 0x20, 0x3d, 0x3e, 0x20, 0x7b, 0x0a, 0x20, 0x20,
-  0x72, 0x65, 0x74, 0x75, 0x72, 0x6e, 0x20, 0x6e, 0x65, 0x77, 0x20, 0x50,
-  0x72, 0x6f, 0x6d, 0x69, 0x73, 0x65, 0x28, 0x61, 0x73, 0x79, 0x6e, 0x63,
-  0x20, 0x28, 0x72, 0x65, 0x73, 0x6f, 0x6c, 0x76, 0x65, 0x2c, 0x20, 0x72,
-  0x65, 0x6a, 0x65, 0x63, 0x74, 0x29, 0x20, 0x3d, 0x3e, 0x20, 0x7b, 0x0a,
-  0x20, 0x20, 0x20, 0x20, 0x6c, 0x65, 0x74, 0x20, 0x63, 0x6f, 0x6e, 0x74,
-  0x65, 0x6e, 0x74, 0x20, 0x3d, 0x20, 0x22, 0x22, 0x3b, 0x0a, 0x20, 0x20,
-  0x20, 0x20, 0x74, 0x72, 0x79, 0x20, 0x7b, 0x0a, 0x20, 0x20, 0x20, 0x20,
+  0x75, 0x6e, 0x6b, 0x2e, 0x64, 0x61, 0x74, 0x61, 0x2e, 0x74, 0x69, 0x6d,
+  0x69, 0x6e, 0x67, 0x73, 0x20, 0x7d, 0x29, 0x29, 0x3b, 0x0a, 0x20, 0x20,
+  0x20, 0x20, 0x20, 0x20, 0x7d, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x7d, 0x0a,
+  0x20, 0x20, 0x20, 0x20, 0x65, 0x76, 0x65, 0x6e, 0x74, 0x54, 0x61, 0x72,
+  0x67, 0x65, 0x74, 0x2e, 0x64, 0x69, 0x73, 0x70, 0x61, 0x74, 0x63, 0x68,
+  0x45, 0x76, 0x65, 0x6e, 0x74, 0x28, 0x6e, 0x65, 0x77, 0x20, 0x43, 0x75,
+  0x73, 0x74, 0x6f, 0x6d, 0x45, 0x76, 0x65, 0x6e, 0x74, 0x28, 0x22, 0x64,
+  0x6f, 0x6e, 0x65, 0x22, 0x2c, 0x20, 0x7b, 0x20, 0x64, 0x65, 0x74, 0x61,
+  0x69, 0x6c, 0x3a, 0x20, 0x7b, 0x20, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e,
+  0x74, 0x20, 0x7d, 0x20, 0x7d, 0x29, 0x29, 0x3b, 0x0a, 0x20, 0x20, 0x7d,
+  0x29, 0x28, 0x29, 0x3b, 0x0a, 0x20, 0x20, 0x72, 0x65, 0x74, 0x75, 0x72,
+  0x6e, 0x20, 0x65, 0x76, 0x65, 0x6e, 0x74, 0x54, 0x61, 0x72, 0x67, 0x65,
+  0x74, 0x3b, 0x0a, 0x7d, 0x0a, 0x0a, 0x2f, 0x2f, 0x20, 0x43, 0x61, 0x6c,
+  0x6c, 0x20, 0x6c, 0x6c, 0x61, 0x6d, 0x61, 0x2c, 0x20, 0x72, 0x65, 0x74,
+  0x75, 0x72, 0x6e, 0x20, 0x61, 0x20, 0x70, 0x72, 0x6f, 0x6d, 0x69, 0x73,
+  0x65, 0x20, 0x74, 0x68, 0x61, 0x74, 0x20, 0x72, 0x65, 0x73, 0x6f, 0x6c,
+  0x76, 0x65, 0x73, 0x20, 0x74, 0x6f, 0x20, 0x74, 0x68, 0x65, 0x20, 0x63,
+  0x6f, 0x6d, 0x70, 0x6c, 0x65, 0x74, 0x65, 0x64, 0x20, 0x74, 0x65, 0x78,
+  0x74, 0x2e, 0x20, 0x54, 0x68, 0x69, 0x73, 0x20, 0x64, 0x6f, 0x65, 0x73,
+  0x20, 0x6e, 0x6f, 0x74, 0x20, 0x73, 0x75, 0x70, 0x70, 0x6f, 0x72, 0x74,
+  0x20, 0x73, 0x74, 0x72, 0x65, 0x61, 0x6d, 0x69, 0x6e, 0x67, 0x0a, 0x2f,
+  0x2f, 0x0a, 0x2f, 0x2f, 0x20, 0x45, 0x78, 0x61, 0x6d, 0x70, 0x6c, 0x65,
+  0x3a, 0x0a, 0x2f, 0x2f, 0x0a, 0x2f, 0x2f, 0x20, 0x20, 0x20, 0x20, 0x20,
+  0x6c, 0x6c, 0x61, 0x6d, 0x61, 0x50, 0x72, 0x6f, 0x6d, 0x69, 0x73, 0x65,
+  0x28, 0x70, 0x72, 0x6f, 0x6d, 0x70, 0x74, 0x29, 0x2e, 0x74, 0x68, 0x65,
+  0x6e, 0x28, 0x28, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x29, 0x20,
+  0x3d, 0x3e, 0x20, 0x7b, 0x0a, 0x2f, 0x2f, 0x20, 0x20, 0x20, 0x20, 0x20,
+  0x20, 0x20, 0x64, 0x6f, 0x63, 0x75, 0x6d, 0x65, 0x6e, 0x74, 0x2e, 0x77,
+  0x72, 0x69, 0x74, 0x65, 0x28, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74,
+  0x29, 0x0a, 0x2f, 0x2f, 0x20, 0x20, 0x20, 0x20, 0x20, 0x7d, 0x29, 0x0a,
+  0x2f, 0x2f, 0x0a, 0x2f, 0x2f, 0x20, 0x20, 0x20, 0x20, 0x20, 0x6f, 0x72,
+  0x0a, 0x2f, 0x2f, 0x0a, 0x2f, 0x2f, 0x20, 0x20, 0x20, 0x20, 0x20, 0x63,
+  0x6f, 0x6e, 0x73, 0x74, 0x20, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74,
+  0x20, 0x3d, 0x20, 0x61, 0x77, 0x61, 0x69, 0x74, 0x20, 0x6c, 0x6c, 0x61,
+  0x6d, 0x61, 0x50, 0x72, 0x6f, 0x6d, 0x69, 0x73, 0x65, 0x28, 0x70, 0x72,
+  0x6f, 0x6d, 0x70, 0x74, 0x29, 0x0a, 0x2f, 0x2f, 0x20, 0x20, 0x20, 0x20,
+  0x20, 0x64, 0x6f, 0x63, 0x75, 0x6d, 0x65, 0x6e, 0x74, 0x2e, 0x77, 0x72,
+  0x69, 0x74, 0x65, 0x28, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x29,
+  0x0a, 0x2f, 0x2f, 0x0a, 0x65, 0x78, 0x70, 0x6f, 0x72, 0x74, 0x20, 0x63,
+  0x6f, 0x6e, 0x73, 0x74, 0x20, 0x6c, 0x6c, 0x61, 0x6d, 0x61, 0x50, 0x72,
+  0x6f, 0x6d, 0x69, 0x73, 0x65, 0x20, 0x3d, 0x20, 0x28, 0x70, 0x72, 0x6f,
+  0x6d, 0x70, 0x74, 0x2c, 0x20, 0x70, 0x61, 0x72, 0x61, 0x6d, 0x73, 0x20,
+  0x3d, 0x20, 0x7b, 0x7d, 0x2c, 0x20, 0x63, 0x6f, 0x6e, 0x66, 0x69, 0x67,
+  0x20, 0x3d, 0x20, 0x7b, 0x7d, 0x29, 0x20, 0x3d, 0x3e, 0x20, 0x7b, 0x0a,
+  0x20, 0x20, 0x72, 0x65, 0x74, 0x75, 0x72, 0x6e, 0x20, 0x6e, 0x65, 0x77,
+  0x20, 0x50, 0x72, 0x6f, 0x6d, 0x69, 0x73, 0x65, 0x28, 0x61, 0x73, 0x79,
+  0x6e, 0x63, 0x20, 0x28, 0x72, 0x65, 0x73, 0x6f, 0x6c, 0x76, 0x65, 0x2c,
+  0x20, 0x72, 0x65, 0x6a, 0x65, 0x63, 0x74, 0x29, 0x20, 0x3d, 0x3e, 0x20,
+  0x7b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x6c, 0x65, 0x74, 0x20, 0x63, 0x6f,
+  0x6e, 0x74, 0x65, 0x6e, 0x74, 0x20, 0x3d, 0x20, 0x22, 0x22, 0x3b, 0x0a,
+  0x20, 0x20, 0x20, 0x20, 0x74, 0x72, 0x79, 0x20, 0x7b, 0x0a, 0x20, 0x20,
+  0x20, 0x20, 0x20, 0x20, 0x66, 0x6f, 0x72, 0x20, 0x61, 0x77, 0x61, 0x69,
+  0x74, 0x20, 0x28, 0x63, 0x6f, 0x6e, 0x73, 0x74, 0x20, 0x63, 0x68, 0x75,
+  0x6e, 0x6b, 0x20, 0x6f, 0x66, 0x20, 0x6c, 0x6c, 0x61, 0x6d, 0x61, 0x28,
+  0x70, 0x72, 0x6f, 0x6d, 0x70, 0x74, 0x2c, 0x20, 0x70, 0x61, 0x72, 0x61,
+  0x6d, 0x73, 0x2c, 0x20, 0x63, 0x6f, 0x6e, 0x66, 0x69, 0x67, 0x29, 0x29,
+  0x20, 0x7b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x63,
+  0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x20, 0x2b, 0x3d, 0x20, 0x63, 0x68,
+  0x75, 0x6e, 0x6b, 0x2e, 0x64, 0x61, 0x74, 0x61, 0x2e, 0x63, 0x6f, 0x6e,
+  0x74, 0x65, 0x6e, 0x74, 0x3b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
+  0x7d, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x72, 0x65, 0x73, 0x6f,
+  0x6c, 0x76, 0x65, 0x28, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x29,
+  0x3b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x7d, 0x20, 0x63, 0x61, 0x74, 0x63,
+  0x68, 0x20, 0x28, 0x65, 0x72, 0x72, 0x6f, 0x72, 0x29, 0x20, 0x7b, 0x0a,
+  0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x72, 0x65, 0x6a, 0x65, 0x63, 0x74,
+  0x28, 0x65, 0x72, 0x72, 0x6f, 0x72, 0x29, 0x3b, 0x0a, 0x20, 0x20, 0x20,
+  0x20, 0x7d, 0x0a, 0x20, 0x20, 0x7d, 0x29, 0x3b, 0x0a, 0x7d, 0x3b, 0x0a,
+  0x0a, 0x2f, 0x2a, 0x2a, 0x0a, 0x20, 0x2a, 0x20, 0x28, 0x64, 0x65, 0x70,
+  0x72, 0x65, 0x63, 0x61, 0x74, 0x65, 0x64, 0x29, 0x0a, 0x20, 0x2a, 0x2f,
+  0x0a, 0x65, 0x78, 0x70, 0x6f, 0x72, 0x74, 0x20, 0x63, 0x6f, 0x6e, 0x73,
+  0x74, 0x20, 0x6c, 0x6c, 0x61, 0x6d, 0x61, 0x43, 0x6f, 0x6d, 0x70, 0x6c,
+  0x65, 0x74, 0x65, 0x20, 0x3d, 0x20, 0x61, 0x73, 0x79, 0x6e, 0x63, 0x20,
+  0x28, 0x70, 0x61, 0x72, 0x61, 0x6d, 0x73, 0x2c, 0x20, 0x63, 0x6f, 0x6e,
+  0x74, 0x72, 0x6f, 0x6c, 0x6c, 0x65, 0x72, 0x2c, 0x20, 0x63, 0x61, 0x6c,
+  0x6c, 0x62, 0x61, 0x63, 0x6b, 0x29, 0x20, 0x3d, 0x3e, 0x20, 0x7b, 0x0a,
   0x20, 0x20, 0x66, 0x6f, 0x72, 0x20, 0x61, 0x77, 0x61, 0x69, 0x74, 0x20,
   0x28, 0x63, 0x6f, 0x6e, 0x73, 0x74, 0x20, 0x63, 0x68, 0x75, 0x6e, 0x6b,
-  0x20, 0x6f, 0x66, 0x20, 0x6c, 0x6c, 0x61, 0x6d, 0x61, 0x28, 0x70, 0x72,
-  0x6f, 0x6d, 0x70, 0x74, 0x2c, 0x20, 0x70, 0x61, 0x72, 0x61, 0x6d, 0x73,
-  0x2c, 0x20, 0x63, 0x6f, 0x6e, 0x66, 0x69, 0x67, 0x29, 0x29, 0x20, 0x7b,
-  0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x63, 0x6f, 0x6e,
-  0x74, 0x65, 0x6e, 0x74, 0x20, 0x2b, 0x3d, 0x20, 0x63, 0x68, 0x75, 0x6e,
-  0x6b, 0x2e, 0x64, 0x61, 0x74, 0x61, 0x2e, 0x63, 0x6f, 0x6e, 0x74, 0x65,
-  0x6e, 0x74, 0x3b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x7d, 0x0a,
-  0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x72, 0x65, 0x73, 0x6f, 0x6c, 0x76,
-  0x65, 0x28, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x29, 0x3b, 0x0a,
-  0x20, 0x20, 0x20, 0x20, 0x7d, 0x20, 0x63, 0x61, 0x74, 0x63, 0x68, 0x20,
-  0x28, 0x65, 0x72, 0x72, 0x6f, 0x72, 0x29, 0x20, 0x7b, 0x0a, 0x20, 0x20,
-  0x20, 0x20, 0x20, 0x20, 0x72, 0x65, 0x6a, 0x65, 0x63, 0x74, 0x28, 0x65,
-  0x72, 0x72, 0x6f, 0x72, 0x29, 0x3b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x7d,
-  0x0a, 0x20, 0x20, 0x7d, 0x29, 0x3b, 0x0a, 0x7d, 0x3b, 0x0a, 0x0a, 0x2f,
-  0x2a, 0x2a, 0x0a, 0x20, 0x2a, 0x20, 0x28, 0x64, 0x65, 0x70, 0x72, 0x65,
-  0x63, 0x61, 0x74, 0x65, 0x64, 0x29, 0x0a, 0x20, 0x2a, 0x2f, 0x0a, 0x65,
-  0x78, 0x70, 0x6f, 0x72, 0x74, 0x20, 0x63, 0x6f, 0x6e, 0x73, 0x74, 0x20,
-  0x6c, 0x6c, 0x61, 0x6d, 0x61, 0x43, 0x6f, 0x6d, 0x70, 0x6c, 0x65, 0x74,
-  0x65, 0x20, 0x3d, 0x20, 0x61, 0x73, 0x79, 0x6e, 0x63, 0x20, 0x28, 0x70,
-  0x61, 0x72, 0x61, 0x6d, 0x73, 0x2c, 0x20, 0x63, 0x6f, 0x6e, 0x74, 0x72,
-  0x6f, 0x6c, 0x6c, 0x65, 0x72, 0x2c, 0x20, 0x63, 0x61, 0x6c, 0x6c, 0x62,
-  0x61, 0x63, 0x6b, 0x29, 0x20, 0x3d, 0x3e, 0x20, 0x7b, 0x0a, 0x20, 0x20,
-  0x66, 0x6f, 0x72, 0x20, 0x61, 0x77, 0x61, 0x69, 0x74, 0x20, 0x28, 0x63,
-  0x6f, 0x6e, 0x73, 0x74, 0x20, 0x63, 0x68, 0x75, 0x6e, 0x6b, 0x20, 0x6f,
-  0x66, 0x20, 0x6c, 0x6c, 0x61, 0x6d, 0x61, 0x28, 0x70, 0x61, 0x72, 0x61,
-  0x6d, 0x73, 0x2e, 0x70, 0x72, 0x6f, 0x6d, 0x70, 0x74, 0x2c, 0x20, 0x70,
-  0x61, 0x72, 0x61, 0x6d, 0x73, 0x2c, 0x20, 0x7b, 0x20, 0x63, 0x6f, 0x6e,
-  0x74, 0x72, 0x6f, 0x6c, 0x6c, 0x65, 0x72, 0x20, 0x7d, 0x29, 0x29, 0x20,
-  0x7b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x63, 0x61, 0x6c, 0x6c, 0x62, 0x61,
-  0x63, 0x6b, 0x28, 0x63, 0x68, 0x75, 0x6e, 0x6b, 0x29, 0x3b, 0x0a, 0x20,
-  0x20, 0x7d, 0x0a, 0x7d, 0x0a, 0x0a, 0x2f, 0x2f, 0x20, 0x47, 0x65, 0x74,
-  0x20, 0x74, 0x68, 0x65, 0x20, 0x6d, 0x6f, 0x64, 0x65, 0x6c, 0x20, 0x69,
-  0x6e, 0x66, 0x6f, 0x20, 0x66, 0x72, 0x6f, 0x6d, 0x20, 0x74, 0x68, 0x65,
-  0x20, 0x73, 0x65, 0x72, 0x76, 0x65, 0x72, 0x2e, 0x20, 0x54, 0x68, 0x69,
-  0x73, 0x20, 0x69, 0x73, 0x20, 0x75, 0x73, 0x65, 0x66, 0x75, 0x6c, 0x20,
-  0x66, 0x6f, 0x72, 0x20, 0x67, 0x65, 0x74, 0x74, 0x69, 0x6e, 0x67, 0x20,
-  0x74, 0x68, 0x65, 0x20, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x78, 0x74, 0x20,
-  0x77, 0x69, 0x6e, 0x64, 0x6f, 0x77, 0x20, 0x61, 0x6e, 0x64, 0x20, 0x73,
-  0x6f, 0x20, 0x6f, 0x6e, 0x2e, 0x0a, 0x65, 0x78, 0x70, 0x6f, 0x72, 0x74,
-  0x20, 0x63, 0x6f, 0x6e, 0x73, 0x74, 0x20, 0x6c, 0x6c, 0x61, 0x6d, 0x61,
-  0x4d, 0x6f, 0x64, 0x65, 0x6c, 0x49, 0x6e, 0x66, 0x6f, 0x20, 0x3d, 0x20,
-  0x61, 0x73, 0x79, 0x6e, 0x63, 0x20, 0x28, 0x29, 0x20, 0x3d, 0x3e, 0x20,
-  0x7b, 0x0a, 0x20, 0x20, 0x69, 0x66, 0x20, 0x28, 0x21, 0x67, 0x65, 0x6e,
-  0x65, 0x72, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x5f, 0x73, 0x65, 0x74, 0x74,
-  0x69, 0x6e, 0x67, 0x73, 0x29, 0x20, 0x7b, 0x0a, 0x20, 0x20, 0x20, 0x20,
-  0x63, 0x6f, 0x6e, 0x73, 0x74, 0x20, 0x70, 0x72, 0x6f, 0x70, 0x73, 0x20,
-  0x3d, 0x20, 0x61, 0x77, 0x61, 0x69, 0x74, 0x20, 0x66, 0x65, 0x74, 0x63,
-  0x68, 0x28, 0x22, 0x2f, 0x70, 0x72, 0x6f, 0x70, 0x73, 0x22, 0x29, 0x2e,
-  0x74, 0x68, 0x65, 0x6e, 0x28, 0x72, 0x20, 0x3d, 0x3e, 0x20, 0x72, 0x2e,
-  0x6a, 0x73, 0x6f, 0x6e, 0x28, 0x29, 0x29, 0x3b, 0x0a, 0x20, 0x20, 0x20,
-  0x20, 0x67, 0x65, 0x6e, 0x65, 0x72, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x5f,
-  0x73, 0x65, 0x74, 0x74, 0x69, 0x6e, 0x67, 0x73, 0x20, 0x3d, 0x20, 0x70,
-  0x72, 0x6f, 0x70, 0x73, 0x2e, 0x64, 0x65, 0x66, 0x61, 0x75, 0x6c, 0x74,
-  0x5f, 0x67, 0x65, 0x6e, 0x65, 0x72, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x5f,
-  0x73, 0x65, 0x74, 0x74, 0x69, 0x6e, 0x67, 0x73, 0x3b, 0x0a, 0x20, 0x20,
-  0x7d, 0x0a, 0x20, 0x20, 0x72, 0x65, 0x74, 0x75, 0x72, 0x6e, 0x20, 0x67,
+  0x20, 0x6f, 0x66, 0x20, 0x6c, 0x6c, 0x61, 0x6d, 0x61, 0x28, 0x70, 0x61,
+  0x72, 0x61, 0x6d, 0x73, 0x2e, 0x70, 0x72, 0x6f, 0x6d, 0x70, 0x74, 0x2c,
+  0x20, 0x70, 0x61, 0x72, 0x61, 0x6d, 0x73, 0x2c, 0x20, 0x7b, 0x20, 0x63,
+  0x6f, 0x6e, 0x74, 0x72, 0x6f, 0x6c, 0x6c, 0x65, 0x72, 0x20, 0x7d, 0x29,
+  0x29, 0x20, 0x7b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x63, 0x61, 0x6c, 0x6c,
+  0x62, 0x61, 0x63, 0x6b, 0x28, 0x63, 0x68, 0x75, 0x6e, 0x6b, 0x29, 0x3b,
+  0x0a, 0x20, 0x20, 0x7d, 0x0a, 0x7d, 0x0a, 0x0a, 0x2f, 0x2f, 0x20, 0x47,
+  0x65, 0x74, 0x20, 0x74, 0x68, 0x65, 0x20, 0x6d, 0x6f, 0x64, 0x65, 0x6c,
+  0x20, 0x69, 0x6e, 0x66, 0x6f, 0x20, 0x66, 0x72, 0x6f, 0x6d, 0x20, 0x74,
+  0x68, 0x65, 0x20, 0x73, 0x65, 0x72, 0x76, 0x65, 0x72, 0x2e, 0x20, 0x54,
+  0x68, 0x69, 0x73, 0x20, 0x69, 0x73, 0x20, 0x75, 0x73, 0x65, 0x66, 0x75,
+  0x6c, 0x20, 0x66, 0x6f, 0x72, 0x20, 0x67, 0x65, 0x74, 0x74, 0x69, 0x6e,
+  0x67, 0x20, 0x74, 0x68, 0x65, 0x20, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x78,
+  0x74, 0x20, 0x77, 0x69, 0x6e, 0x64, 0x6f, 0x77, 0x20, 0x61, 0x6e, 0x64,
+  0x20, 0x73, 0x6f, 0x20, 0x6f, 0x6e, 0x2e, 0x0a, 0x65, 0x78, 0x70, 0x6f,
+  0x72, 0x74, 0x20, 0x63, 0x6f, 0x6e, 0x73, 0x74, 0x20, 0x6c, 0x6c, 0x61,
+  0x6d, 0x61, 0x4d, 0x6f, 0x64, 0x65, 0x6c, 0x49, 0x6e, 0x66, 0x6f, 0x20,
+  0x3d, 0x20, 0x61, 0x73, 0x79, 0x6e, 0x63, 0x20, 0x28, 0x29, 0x20, 0x3d,
+  0x3e, 0x20, 0x7b, 0x0a, 0x20, 0x20, 0x69, 0x66, 0x20, 0x28, 0x21, 0x67,
   0x65, 0x6e, 0x65, 0x72, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x5f, 0x73, 0x65,
-  0x74, 0x74, 0x69, 0x6e, 0x67, 0x73, 0x3b, 0x0a, 0x7d, 0x0a
+  0x74, 0x74, 0x69, 0x6e, 0x67, 0x73, 0x29, 0x20, 0x7b, 0x0a, 0x20, 0x20,
+  0x20, 0x20, 0x63, 0x6f, 0x6e, 0x73, 0x74, 0x20, 0x70, 0x72, 0x6f, 0x70,
+  0x73, 0x20, 0x3d, 0x20, 0x61, 0x77, 0x61, 0x69, 0x74, 0x20, 0x66, 0x65,
+  0x74, 0x63, 0x68, 0x28, 0x22, 0x2f, 0x70, 0x72, 0x6f, 0x70, 0x73, 0x22,
+  0x29, 0x2e, 0x74, 0x68, 0x65, 0x6e, 0x28, 0x72, 0x20, 0x3d, 0x3e, 0x20,
+  0x72, 0x2e, 0x6a, 0x73, 0x6f, 0x6e, 0x28, 0x29, 0x29, 0x3b, 0x0a, 0x20,
+  0x20, 0x20, 0x20, 0x67, 0x65, 0x6e, 0x65, 0x72, 0x61, 0x74, 0x69, 0x6f,
+  0x6e, 0x5f, 0x73, 0x65, 0x74, 0x74, 0x69, 0x6e, 0x67, 0x73, 0x20, 0x3d,
+  0x20, 0x70, 0x72, 0x6f, 0x70, 0x73, 0x2e, 0x64, 0x65, 0x66, 0x61, 0x75,
+  0x6c, 0x74, 0x5f, 0x67, 0x65, 0x6e, 0x65, 0x72, 0x61, 0x74, 0x69, 0x6f,
+  0x6e, 0x5f, 0x73, 0x65, 0x74, 0x74, 0x69, 0x6e, 0x67, 0x73, 0x3b, 0x0a,
+  0x20, 0x20, 0x7d, 0x0a, 0x20, 0x20, 0x72, 0x65, 0x74, 0x75, 0x72, 0x6e,
+  0x20, 0x67, 0x65, 0x6e, 0x65, 0x72, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x5f,
+  0x73, 0x65, 0x74, 0x74, 0x69, 0x6e, 0x67, 0x73, 0x3b, 0x0a, 0x7d, 0x0a
 };
-unsigned int completion_js_len = 5782;
+unsigned int completion_js_len = 5796;
diff --git a/examples/server/public/completion.js b/examples/server/public/completion.js
index ab38a7b40..835ce6e68 100644
--- a/examples/server/public/completion.js
+++ b/examples/server/public/completion.js
@@ -96,18 +96,18 @@ export async function* llama(prompt, params = {}, config = {}) {
             }
           }
           if (result.error) {
-            result.error = JSON.parse(result.error);
-            if (result.error.content.includes('slot unavailable')) {
-              // Throw an error to be caught by upstream callers
-              throw new Error('slot unavailable');
-            } else {
-              console.error(`llama.cpp error: ${result.error.content}`);
+            try {
+              result.error = JSON.parse(result.error);
+              if (result.error.message.includes('slot unavailable')) {
+                // Throw an error to be caught by upstream callers
+                throw new Error('slot unavailable');
+              } else {
+                console.error(`llama.cpp error [${result.error.code} - ${result.error.type}]: ${result.error.message}`);
+              }
+            } catch(e) {
+              console.error(`llama.cpp error ${result.error}`)
             }
           }
-          if (result.error) {
-            result.error = JSON.parse(result.error);
-            console.error(`llama.cpp error: ${result.error.content}`);
-          }
         }
       }
     }
diff --git a/examples/server/server.cpp b/examples/server/server.cpp
index 88be0e61f..5d334f63d 100644
--- a/examples/server/server.cpp
+++ b/examples/server/server.cpp
@@ -28,6 +28,7 @@
 #include <mutex>
 #include <thread>
 #include <signal.h>
+#include <memory>
 
 using json = nlohmann::json;
 
@@ -113,12 +114,17 @@ struct server_params {
     int32_t n_threads_http = -1;
 
     std::string hostname      = "127.0.0.1";
-    std::string public_path   = "examples/server/public";
+    std::string public_path   = "";
     std::string chat_template = "";
     std::string system_prompt = "";
 
     std::vector<std::string> api_keys;
 
+#ifdef CPPHTTPLIB_OPENSSL_SUPPORT
+    std::string ssl_key_file = "";
+    std::string ssl_cert_file = "";
+#endif
+
     bool slots_endpoint   = true;
     bool metrics_endpoint = false;
 };
@@ -336,7 +342,7 @@ struct server_slot {
 };
 
 struct server_metrics {
-    const int64_t t_start = ggml_time_us();
+    int64_t t_start = 0;
 
     uint64_t n_prompt_tokens_processed_total = 0;
     uint64_t t_prompt_processing_total       = 0;
@@ -349,14 +355,18 @@ struct server_metrics {
     uint64_t n_tokens_predicted  = 0;
     uint64_t t_tokens_generation = 0;
 
-    void on_prompt_eval(const server_slot &slot) {
+    void init() {
+        t_start = ggml_time_us();
+    }
+
+    void on_prompt_eval(const server_slot & slot) {
         n_prompt_tokens_processed_total += slot.n_prompt_tokens_processed;
         n_prompt_tokens_processed       += slot.n_prompt_tokens_processed;
         t_prompt_processing             += slot.t_prompt_processing;
         t_prompt_processing_total       += slot.t_prompt_processing;
     }
 
-    void on_prediction(const server_slot &slot) {
+    void on_prediction(const server_slot & slot) {
         n_tokens_predicted_total   += slot.n_decoded;
         n_tokens_predicted         += slot.n_decoded;
         t_tokens_generation        += slot.t_token_generation;
@@ -387,7 +397,7 @@ struct server_queue {
     // callback functions
     std::function<void(server_task       &)> callback_new_task;
     std::function<void(server_task_multi &)> callback_finish_multitask;
-    std::function<void(void)>                callback_run_slots;
+    std::function<void(void)>                callback_update_slots;
 
     // Add a new task to the end of the queue
     int post(server_task task) {
@@ -426,8 +436,8 @@ struct server_queue {
     }
 
     // Register the function to be called when all slots data is ready to be processed
-    void on_run_slots(std::function<void(void)> callback) {
-        callback_run_slots = std::move(callback);
+    void on_update_slots(std::function<void(void)> callback) {
+        callback_update_slots = std::move(callback);
     }
 
     // Call when the state of one slot is changed
@@ -452,7 +462,7 @@ struct server_queue {
      * - Wait until a new task arrives
      * - Process the task (i.e. maybe copy data into slot)
      * - Check if multitask is finished
-     * - Run all slots
+     * - Update all slots
      */
     void start_loop() {
         running = true;
@@ -490,9 +500,9 @@ struct server_queue {
             }
 
             // all tasks in the current loop is processed, slots data is now ready
-            LOG_VERBOSE("callback_run_slots", {});
+            LOG_VERBOSE("callback_update_slots", {});
 
-            callback_run_slots();
+            callback_update_slots();
 
             LOG_VERBOSE("wait for new task", {});
             {
@@ -685,10 +695,11 @@ struct server_context {
         return res > 0;
     }
 
-    void initialize() {
+    void init() {
         const int32_t n_ctx_slot = n_ctx / params.n_parallel;
 
         LOG_INFO("initializing slots", {{"n_slots", params.n_parallel}});
+
         for (int i = 0; i < params.n_parallel; i++) {
             server_slot slot;
 
@@ -730,6 +741,8 @@ struct server_context {
         default_generation_settings_for_props["seed"] = -1;
 
         batch = llama_batch_init(n_ctx, 0, params.n_parallel);
+
+        metrics.init();
     }
 
     std::vector<llama_token> tokenize(const json & json_prompt, bool add_bos) const {
@@ -793,9 +806,10 @@ struct server_context {
         return last_used;
     }
 
-    bool launch_slot_with_data(server_slot & slot, json data) const {
+    bool launch_slot_with_task(server_slot & slot, const server_task & task) {
         slot_params default_params;
         llama_sampling_params default_sparams;
+        auto & data = task.data;
 
         if (data.count("__oaicompat") != 0) {
             slot.oaicompat = true;
@@ -847,7 +861,21 @@ struct server_context {
         // infill
         slot.params.input_prefix = json_value(data, "input_prefix", default_params.input_prefix);
         slot.params.input_suffix = json_value(data, "input_suffix", default_params.input_suffix);
-        slot.prompt              = json_value(data, "prompt",       std::string(""));
+
+        // get prompt
+        {
+            const auto & prompt = data.find("prompt");
+            if (prompt == data.end()) {
+                send_error(task, "Either \"prompt\" or \"messages\" must be provided", ERROR_TYPE_INVALID_REQUEST);
+                return false;
+            } else {
+                slot.prompt = *prompt;
+            }
+            if (slot.prompt.is_array() && slot.prompt.size() == 0) {
+                send_error(task, "\"prompt\" cannot be an empty array", ERROR_TYPE_INVALID_REQUEST);
+                return false;
+            }
+        }
 
         // penalize user-provided tokens
         {
@@ -905,6 +933,7 @@ struct server_context {
             if (logit_bias != data.end() && logit_bias->is_array()) {
                 const int n_vocab = llama_n_vocab(model);
                 for (const auto & el : *logit_bias) {
+                    // TODO: we may want to throw errors here, in case "el" is incorrect
                     if (el.is_array() && el.size() == 2) {
                         float bias;
                         if (el[1].is_number()) {
@@ -964,6 +993,11 @@ struct server_context {
                 llama_sampling_free(slot.ctx_sampling);
             }
             slot.ctx_sampling = llama_sampling_init(slot.sparams);
+            if (slot.ctx_sampling == nullptr) {
+                // for now, the only error that may happen here is invalid grammar
+                send_error(task, "Failed to parse grammar", ERROR_TYPE_INVALID_REQUEST);
+                return false;
+            }
             llama_set_rng_seed(ctx, slot.params.seed);
         }
 
@@ -1129,6 +1163,7 @@ struct server_context {
 
             LOG_VERBOSE("stopped by limit", {
                 {"id_slot",   slot.id},
+                {"id_task",   slot.id_task},
                 {"n_decoded", slot.n_decoded},
                 {"n_predict", slot.params.n_predict},
             });
@@ -1142,6 +1177,8 @@ struct server_context {
         }
 
         LOG_VERBOSE("next token", {
+            {"id_slot",        slot.id},
+            {"id_task",        slot.id_task},
             {"token",          result.tok},
             {"token_text",     tokens_to_output_formatted_string(ctx, result.tok)},
             {"has_next_token", slot.has_next_token},
@@ -1202,15 +1239,23 @@ struct server_context {
         };
     }
 
-    void send_error(const server_task & task, const std::string & error) {
-        LOG_TEE("task %i - error: %s\n", task.id, error.c_str());
+    void send_error(const server_task & task, const std::string & error, const enum error_type type = ERROR_TYPE_SERVER) {
+        send_error(task.id, task.id_multi, error, type);
+    }
+
+    void send_error(const server_slot & slot, const std::string & error, const enum error_type type = ERROR_TYPE_SERVER) {
+        send_error(slot.id_task, slot.id_multi, error, type);
+    }
+
+    void send_error(const int id_task, const int id_multi, const std::string & error, const enum error_type type = ERROR_TYPE_SERVER) {
+        LOG_TEE("task %i - error: %s\n", id_task, error.c_str());
 
         server_task_result res;
-        res.id       = task.id;
-        res.id_multi = task.id_multi;
+        res.id       = id_task;
+        res.id_multi = id_multi;
         res.stop     = false;
         res.error    = true;
-        res.data     = { { "content", error } };
+        res.data     = format_error_response(error, type);
 
         queue_results.send(res);
     }
@@ -1310,6 +1355,8 @@ struct server_context {
 
         const int n_embd = llama_n_embd(model);
 
+        std::vector<float> embd_res(n_embd, 0.0f);
+
         for (int i = 0; i < batch.n_tokens; ++i) {
             if (!batch.logits[i] || batch.seq_id[i][0] != slot.id + 1) {
                 continue;
@@ -1333,8 +1380,10 @@ struct server_context {
                 continue;
             }
 
+            llama_embd_normalize(embd, embd_res.data(), n_embd);
+
             res.data = json {
-                {"embedding", std::vector<float>(embd, embd + n_embd)},
+                {"embedding", embd_res},
             };
         }
 
@@ -1440,9 +1489,8 @@ struct server_context {
                     slot->infill    = task.infill;
                     slot->embedding = task.embedding;
 
-                    if (!launch_slot_with_data(*slot, task.data)) {
-                        // send error result
-                        send_error(task, "internal_error");
+                    if (!launch_slot_with_task(*slot, task)) {
+                        LOG_ERROR("error while launching slot", task.data);
                         break;
                     }
                 } break;
@@ -1559,7 +1607,7 @@ struct server_context {
         queue_results.send(result);
     }
 
-    bool update_slots() {
+    void update_slots() {
         if (system_need_update) {
             system_prompt_update();
         }
@@ -1602,7 +1650,7 @@ struct server_context {
                     kv_cache_clear();
                 }
 
-                return true;
+                return;
             }
         }
 
@@ -1696,19 +1744,6 @@ struct server_context {
         // next, batch any pending prompts without exceeding n_batch
         if (params.cont_batching || batch.n_tokens == 0) {
             for (auto & slot : slots) {
-                const bool has_prompt = slot.prompt.is_array() || (slot.prompt.is_string() && !slot.prompt.get<std::string>().empty());
-
-                // empty prompt passed -> release the slot and send empty response
-                // note: infill mode allows empty prompt
-                if (slot.state == SLOT_STATE_IDLE && slot.command == SLOT_COMMAND_LOAD_PROMPT && !has_prompt && !slot.infill) {
-                    slot.state = SLOT_STATE_PROCESSING;
-                    slot.command = SLOT_COMMAND_NONE;
-                    slot.release();
-                    slot.print_timings();
-                    send_final_response(slot);
-                    continue;
-                }
-
                 // this slot still has a prompt to be processed
                 if (slot.state == SLOT_STATE_IDLE && slot.command == SLOT_COMMAND_LOAD_PROMPT) {
                     auto & prompt_tokens = slot.prompt_tokens;
@@ -1751,6 +1786,30 @@ struct server_context {
                         slot.n_past = 0;
                         slot.n_prompt_tokens = prompt_tokens.size();
 
+                        LOG_VERBOSE("prompt tokenized", {
+                            {"id_slot",         slot.id},
+                            {"id_task",         slot.id_task},
+                            {"n_ctx",           slot.n_ctx},
+                            {"n_keep",          slot.params.n_keep},
+                            {"n_prompt_tokens", slot.n_prompt_tokens},
+                            {"prompt_tokens",   tokens_to_str(ctx, prompt_tokens.cbegin(), prompt_tokens.cend())},
+                        });
+
+                        // empty prompt passed -> release the slot and send empty response
+                        if (prompt_tokens.empty()) {
+                            LOG_INFO("empty prompt - releasing slot", {
+                                {"id_slot", slot.id},
+                                {"id_task", slot.id_task}
+                            });
+
+                            slot.state = SLOT_STATE_PROCESSING;
+                            slot.command = SLOT_COMMAND_NONE;
+                            slot.release();
+                            slot.print_timings();
+                            send_final_response(slot);
+                            continue;
+                        }
+
                         if (slot.embedding) {
                             // this prompt is too large to process - discard it
                             if (slot.n_prompt_tokens > n_batch) {
@@ -1789,10 +1848,13 @@ struct server_context {
                                 slot.n_prompt_tokens = prompt_tokens.size();
 
                                 LOG_VERBOSE("input truncated", {
-                                    {"n_ctx",         slot.n_ctx},
-                                    {"n_keep",        slot.params.n_keep},
-                                    {"n_left",        n_left},
-                                    {"prompt_tokens", tokens_to_str(ctx, prompt_tokens.cbegin(), prompt_tokens.cend())},
+                                    {"id_slot",         slot.id},
+                                    {"id_task",         slot.id_task},
+                                    {"n_ctx",           slot.n_ctx},
+                                    {"n_keep",          slot.params.n_keep},
+                                    {"n_left",          n_left},
+                                    {"n_prompt_tokens", slot.n_prompt_tokens},
+                                    {"prompt_tokens",   tokens_to_str(ctx, prompt_tokens.cbegin(), prompt_tokens.cend())},
                                 });
 
                                 GGML_ASSERT(slot.n_prompt_tokens < slot.n_ctx);
@@ -1933,8 +1995,7 @@ struct server_context {
 
         if (batch.n_tokens == 0) {
             LOG_VERBOSE("no tokens to decode", {});
-
-            return true;
+            return;
         }
 
         LOG_VERBOSE("decoding batch", {
@@ -1991,7 +2052,13 @@ struct server_context {
                 if (n_batch == 1 || ret < 0) {
                     // if you get here, it means the KV cache is full - try increasing it via the context size
                     LOG_TEE("%s : failed to decode the batch, n_batch = %d, ret = %d\n", __func__, n_batch, ret);
-                    return false;
+                    for (auto & slot : slots) {
+                        slot.state = SLOT_STATE_PROCESSING;
+                        slot.command = SLOT_COMMAND_NONE;
+                        slot.release();
+                        send_error(slot, "Input prompt is too big compared to KV size. Please try increasing KV size.");
+                    }
+                    break; // break loop of n_batch
                 }
 
                 LOG_TEE("%s : failed to find free space in the KV cache, retrying with smaller n_batch = %d\n", __func__, n_batch / 2);
@@ -2000,12 +2067,12 @@ struct server_context {
                 n_batch /= 2;
                 i -= n_batch;
 
-                continue;
+                continue; // continue loop of n_batch
             }
 
             for (auto & slot : slots) {
                 if (slot.state != SLOT_STATE_PROCESSING || slot.i_batch < (int) i || slot.i_batch >= (int) (i + n_tokens)) {
-                    continue;
+                    continue; // continue loop of slots
                 }
 
                 // prompt evaluated for embedding
@@ -2013,7 +2080,7 @@ struct server_context {
                     send_embedding(slot, batch_view);
                     slot.release();
                     slot.i_batch = -1;
-                    continue;
+                    continue; // continue loop of slots
                 }
 
                 completion_token_output result;
@@ -2055,9 +2122,7 @@ struct server_context {
             }
         }
 
-        LOG_VERBOSE("slots updated", {});
-
-        return true;
+        LOG_VERBOSE("run slots completed", {});
     }
 
     json model_meta() const {
@@ -2091,6 +2156,8 @@ static void server_print_usage(const char * argv0, const gpt_params & params, co
     printf("  --yarn-beta-slow N        YaRN: high correction dim or alpha (default: %.1f)\n", params.yarn_beta_slow);
     printf("  --yarn-beta-fast N        YaRN: low correction dim or beta (default: %.1f)\n", params.yarn_beta_fast);
     printf("  --pooling {none,mean,cls} pooling type for embeddings, use model default if unspecified\n");
+    printf("  -dt N, --defrag-thold N\n");
+    printf("                            KV cache defragmentation threshold (default: %.1f, < 0 - disabled)\n", params.defrag_thold);
     printf("  -b N, --batch-size N      batch size for prompt processing (default: %d)\n", params.n_batch);
     printf("  --memory-f32              use f32 instead of f16 for memory key+value (default: disabled)\n");
     printf("                            not recommended: doubles context memory required and no measurable increase in quality\n");
@@ -2125,9 +2192,13 @@ static void server_print_usage(const char * argv0, const gpt_params & params, co
     printf("  --lora-base FNAME         optional model to use as a base for the layers modified by the LoRA adapter\n");
     printf("  --host                    ip address to listen (default  (default: %s)\n", sparams.hostname.c_str());
     printf("  --port PORT               port to listen (default  (default: %d)\n", sparams.port);
-    printf("  --path PUBLIC_PATH        path from which to serve static files (default %s)\n", sparams.public_path.c_str());
+    printf("  --path PUBLIC_PATH        path from which to serve static files (default: disabled)\n");
     printf("  --api-key API_KEY         optional api key to enhance server security. If set, requests must include this key for access.\n");
     printf("  --api-key-file FNAME      path to file containing api keys delimited by new lines. If set, requests must include one of the keys for access.\n");
+#ifdef CPPHTTPLIB_OPENSSL_SUPPORT
+    printf("  --ssl-key-file FNAME      path to file a PEM-encoded SSL private key\n");
+    printf("  --ssl-cert-file FNAME     path to file a PEM-encoded SSL certificate\n");
+#endif
     printf("  -to N, --timeout N        server read/write timeout in seconds (default: %d)\n", sparams.read_timeout);
     printf("  --embeddings              enable embedding vector output (default: %s)\n", params.embedding ? "enabled" : "disabled");
     printf("  -np N, --parallel N       number of slots for process requests (default: %d)\n", params.n_parallel);
@@ -2151,7 +2222,8 @@ static void server_print_usage(const char * argv0, const gpt_params & params, co
     printf("  -gaw N, --grp-attn-w N    set the group attention width to extend context size through self-extend(default: 512), used together with group attention factor `--grp-attn-n`\n");
     printf("  --chat-template JINJA_TEMPLATE\n");
     printf("                            set custom jinja chat template (default: template taken from model's metadata)\n");
-    printf("                            Note: only commonly used templates are accepted, since we don't have jinja parser\n");
+    printf("                            only commonly used templates are accepted:\n");
+    printf("                            https://github.com/ggerganov/llama.cpp/wiki/Templates-supported-by-llama_chat_apply_template\n");
     printf("\n");
 }
 
@@ -2187,7 +2259,7 @@ static void server_params_parse(int argc, char ** argv, server_params & sparams,
                 invalid_param = true;
                 break;
             }
-            sparams.api_keys.emplace_back(argv[i]);
+            sparams.api_keys.push_back(argv[i]);
         } else if (arg == "--api-key-file") {
             if (++i >= argc) {
                 invalid_param = true;
@@ -2206,7 +2278,24 @@ static void server_params_parse(int argc, char ** argv, server_params & sparams,
                }
             }
             key_file.close();
-        } else if (arg == "--timeout" || arg == "-to") {
+
+        }
+#ifdef CPPHTTPLIB_OPENSSL_SUPPORT
+        else if (arg == "--ssl-key-file") {
+            if (++i >= argc) {
+                invalid_param = true;
+                break;
+            }
+            sparams.ssl_key_file = argv[i];
+        } else if (arg == "--ssl-cert-file") {
+            if (++i >= argc) {
+                invalid_param = true;
+                break;
+            }
+            sparams.ssl_cert_file = argv[i];
+        }
+#endif
+        else if (arg == "--timeout" || arg == "-to") {
             if (++i >= argc) {
                 invalid_param = true;
                 break;
@@ -2291,6 +2380,12 @@ static void server_params_parse(int argc, char ** argv, server_params & sparams,
             else if (value == "mean") { params.pooling_type = LLAMA_POOLING_TYPE_MEAN; }
             else if (value == "cls")  { params.pooling_type = LLAMA_POOLING_TYPE_CLS; }
             else { invalid_param = true; break; }
+        } else if (arg == "--defrag-thold" || arg == "-dt") {
+            if (++i >= argc) {
+                invalid_param = true;
+                break;
+            }
+            params.defrag_thold = std::stof(argv[i]);
         } else if (arg == "--threads" || arg == "-t") {
             if (++i >= argc)
             {
@@ -2644,21 +2739,186 @@ int main(int argc, char ** argv) {
         {"system_info",     llama_print_system_info()},
     });
 
-    httplib::Server svr;
+    std::unique_ptr<httplib::Server> svr;
+#ifdef CPPHTTPLIB_OPENSSL_SUPPORT
+    if (sparams.ssl_key_file != "" && sparams.ssl_cert_file != "") {
+        LOG_INFO("Running with SSL", {{"key", sparams.ssl_key_file}, {"cert", sparams.ssl_cert_file}});
+        svr.reset(
+            new httplib::SSLServer(sparams.ssl_cert_file.c_str(), sparams.ssl_key_file.c_str())
+        );
+    } else {
+        LOG_INFO("Running without SSL", {});
+        svr.reset(new httplib::Server());
+    }
+#else
+    svr.reset(new httplib::Server());
+#endif
 
     std::atomic<server_state> state{SERVER_STATE_LOADING_MODEL};
 
-    svr.set_default_headers({{"Server", "llama.cpp"}});
+    svr->set_default_headers({{"Server", "llama.cpp"}});
 
     // CORS preflight
-    svr.Options(R"(.*)", [](const httplib::Request & req, httplib::Response & res) {
+    svr->Options(R"(.*)", [](const httplib::Request & req, httplib::Response & res) {
         res.set_header("Access-Control-Allow-Origin",      req.get_header_value("Origin"));
         res.set_header("Access-Control-Allow-Credentials", "true");
         res.set_header("Access-Control-Allow-Methods",     "POST");
         res.set_header("Access-Control-Allow-Headers",     "*");
     });
 
-    svr.Get("/health", [&](const httplib::Request & req, httplib::Response & res) {
+    svr->set_logger(log_server_request);
+
+    auto res_error = [](httplib::Response & res, json error_data) {
+        json final_response {{"error", error_data}};
+        res.set_content(final_response.dump(), "application/json; charset=utf-8");
+        res.status = json_value(error_data, "code", 500);
+    };
+
+    svr->set_exception_handler([&res_error](const httplib::Request &, httplib::Response & res, std::exception_ptr ep) {
+        std::string message;
+        try {
+            std::rethrow_exception(std::move(ep));
+        } catch (std::exception & e) {
+            message = e.what();
+        } catch (...) {
+            message = "Unknown Exception";
+        }
+
+        json formatted_error = format_error_response(message, ERROR_TYPE_SERVER);
+        LOG_VERBOSE("Got exception", formatted_error);
+        res_error(res, formatted_error);
+    });
+
+    svr->set_error_handler([&res_error](const httplib::Request &, httplib::Response & res) {
+        if (res.status == 404) {
+            res_error(res, format_error_response("File Not Found", ERROR_TYPE_NOT_FOUND));
+        }
+        // for other error codes, we skip processing here because it's already done by res_error()
+    });
+
+    // set timeouts and change hostname and port
+    svr->set_read_timeout (sparams.read_timeout);
+    svr->set_write_timeout(sparams.write_timeout);
+
+    if (!svr->bind_to_port(sparams.hostname, sparams.port)) {
+        fprintf(stderr, "\ncouldn't bind to server socket: hostname=%s port=%d\n\n", sparams.hostname.c_str(), sparams.port);
+        return 1;
+    }
+
+    std::unordered_map<std::string, std::string> log_data;
+
+    log_data["hostname"] = sparams.hostname;
+    log_data["port"]     = std::to_string(sparams.port);
+
+    if (sparams.api_keys.size() == 1) {
+        auto key = sparams.api_keys[0];
+        log_data["api_key"] = "api_key: ****" + key.substr(std::max((int)(key.length() - 4), 0));
+    } else if (sparams.api_keys.size() > 1) {
+        log_data["api_key"] = "api_key: " + std::to_string(sparams.api_keys.size()) + " keys loaded";
+    }
+
+    // load the model
+    if (!ctx_server.load_model(params)) {
+        state.store(SERVER_STATE_ERROR);
+        return 1;
+    } else {
+        ctx_server.init();
+        state.store(SERVER_STATE_READY);
+    }
+
+    LOG_INFO("model loaded", {});
+
+    const auto model_meta = ctx_server.model_meta();
+
+    // if a custom chat template is not supplied, we will use the one that comes with the model (if any)
+    if (sparams.chat_template.empty()) {
+        if (!ctx_server.validate_model_chat_template()) {
+            LOG_ERROR("The chat template that comes with this model is not yet supported, falling back to chatml. This may cause the model to output suboptimal responses", {});
+            sparams.chat_template = "chatml";
+        }
+    }
+
+    // print sample chat example to make it clear which template is used
+    {
+        json chat;
+        chat.push_back({{"role", "system"},    {"content", "You are a helpful assistant"}});
+        chat.push_back({{"role", "user"},      {"content", "Hello"}});
+        chat.push_back({{"role", "assistant"}, {"content", "Hi there"}});
+        chat.push_back({{"role", "user"},      {"content", "How are you?"}});
+
+        const std::string chat_example = format_chat(ctx_server.model, sparams.chat_template, chat);
+
+        LOG_INFO("chat template", {
+            {"chat_example", chat_example},
+            {"built_in", sparams.chat_template.empty()},
+        });
+    }
+
+    //
+    // Middlewares
+    //
+
+    auto middleware_validate_api_key = [&sparams, &res_error](const httplib::Request & req, httplib::Response & res) {
+        // TODO: should we apply API key to all endpoints, including "/health" and "/models"?
+        static const std::set<std::string> protected_endpoints = {
+            "/props",
+            "/completion",
+            "/completions",
+            "/v1/completions",
+            "/chat/completions",
+            "/v1/chat/completions",
+            "/infill",
+            "/tokenize",
+            "/detokenize",
+            "/embedding",
+            "/embeddings",
+            "/v1/embeddings",
+        };
+
+        // If API key is not set, skip validation
+        if (sparams.api_keys.empty()) {
+            return true;
+        }
+
+        // If path is not in protected_endpoints list, skip validation
+        if (protected_endpoints.find(req.path) == protected_endpoints.end()) {
+            return true;
+        }
+
+        // Check for API key in the header
+        auto auth_header = req.get_header_value("Authorization");
+
+        std::string prefix = "Bearer ";
+        if (auth_header.substr(0, prefix.size()) == prefix) {
+            std::string received_api_key = auth_header.substr(prefix.size());
+            if (std::find(sparams.api_keys.begin(), sparams.api_keys.end(), received_api_key) != sparams.api_keys.end()) {
+                return true; // API key is valid
+            }
+        }
+
+        // API key is invalid or not provided
+        // TODO: make another middleware for CORS related logic
+        res.set_header("Access-Control-Allow-Origin", req.get_header_value("Origin"));
+        res_error(res, format_error_response("Invalid API Key", ERROR_TYPE_AUTHENTICATION));
+
+        LOG_WARNING("Unauthorized: Invalid API Key", {});
+
+        return false;
+    };
+
+    // register server middlewares
+    svr->set_pre_routing_handler([&middleware_validate_api_key](const httplib::Request & req, httplib::Response & res) {
+        if (!middleware_validate_api_key(req, res)) {
+            return httplib::Server::HandlerResponse::Handled;
+        }
+        return httplib::Server::HandlerResponse::Unhandled;
+    });
+
+    //
+    // Route handlers (or controllers)
+    //
+
+    const auto handle_health = [&](const httplib::Request & req, httplib::Response & res) {
         server_state current_state = state.load();
         switch (current_state) {
             case SERVER_STATE_READY:
@@ -2702,261 +2962,141 @@ int main(int argc, char ** argv) {
                 }
             case SERVER_STATE_LOADING_MODEL:
                 {
-                    res.set_content(R"({"status": "loading model"})", "application/json");
-                    res.status = 503; // HTTP Service Unavailable
+                    res_error(res, format_error_response("Loading model", ERROR_TYPE_UNAVAILABLE));
                 } break;
             case SERVER_STATE_ERROR:
                 {
-                    res.set_content(R"({"status": "error", "error": "Model failed to load"})", "application/json");
-                    res.status = 500; // HTTP Internal Server Error
+                    res_error(res, format_error_response("Model failed to load", ERROR_TYPE_SERVER));
                 } break;
         }
-    });
-
-    if (sparams.slots_endpoint) {
-        svr.Get("/slots", [&](const httplib::Request &, httplib::Response & res) {
-            // request slots data using task queue
-            server_task task;
-            task.id = ctx_server.queue_tasks.get_new_id();
-            task.id_multi  = -1;
-            task.id_target = -1;
-            task.type = SERVER_TASK_TYPE_METRICS;
-
-            ctx_server.queue_results.add_waiting_task_id(task.id);
-            ctx_server.queue_tasks.post(task);
-
-            // get the result
-            server_task_result result = ctx_server.queue_results.recv(task.id);
-            ctx_server.queue_results.remove_waiting_task_id(task.id);
-
-            res.set_content(result.data["slots"].dump(), "application/json");
-            res.status = 200; // HTTP OK
-        });
-    }
-
-    if (sparams.metrics_endpoint) {
-        svr.Get("/metrics", [&](const httplib::Request &, httplib::Response & res) {
-            // request slots data using task queue
-            server_task task;
-            task.id = ctx_server.queue_tasks.get_new_id();
-            task.id_multi  = -1;
-            task.id_target = -1;
-            task.type = SERVER_TASK_TYPE_METRICS;
-            task.data.push_back({{"reset_bucket", true}});
-
-            ctx_server.queue_results.add_waiting_task_id(task.id);
-            ctx_server.queue_tasks.post(task);
-
-            // get the result
-            server_task_result result = ctx_server.queue_results.recv(task.id);
-            ctx_server.queue_results.remove_waiting_task_id(task.id);
-
-            json data = result.data;
-
-            const uint64_t n_prompt_tokens_processed = data["n_prompt_tokens_processed"];
-            const uint64_t t_prompt_processing       = data["t_prompt_processing"];
-
-            const uint64_t n_tokens_predicted  = data["n_tokens_predicted"];
-            const uint64_t t_tokens_generation = data["t_tokens_generation"];
-
-            const int32_t kv_cache_used_cells = data["kv_cache_used_cells"];
-
-            // metrics definition: https://prometheus.io/docs/practices/naming/#metric-names
-            json all_metrics_def = json {
-                {"counter", {{
-                        {"name",  "prompt_tokens_total"},
-                        {"help",  "Number of prompt tokens processed."},
-                        {"value",  (uint64_t) data["n_prompt_tokens_processed_total"]}
-                }, {
-                        {"name",  "prompt_seconds_total"},
-                        {"help",  "Prompt process time"},
-                        {"value",  (uint64_t) data["t_prompt_processing_total"] / 1.e3}
-                }, {
-                        {"name",  "tokens_predicted_total"},
-                        {"help",  "Number of generation tokens processed."},
-                        {"value",  (uint64_t) data["n_tokens_predicted_total"]}
-                }, {
-                        {"name",  "tokens_predicted_seconds_total"},
-                        {"help",  "Predict process time"},
-                        {"value",  (uint64_t) data["t_tokens_generation_total"] / 1.e3}
-                }}},
-                {"gauge", {{
-                        {"name",  "prompt_tokens_seconds"},
-                        {"help",  "Average prompt throughput in tokens/s."},
-                        {"value",  n_prompt_tokens_processed ? 1.e3 / t_prompt_processing * n_prompt_tokens_processed : 0.}
-                },{
-                        {"name",  "predicted_tokens_seconds"},
-                        {"help",  "Average generation throughput in tokens/s."},
-                        {"value",  n_tokens_predicted ? 1.e3 / t_tokens_generation * n_tokens_predicted : 0.}
-                },{
-                        {"name",  "kv_cache_usage_ratio"},
-                        {"help",  "KV-cache usage. 1 means 100 percent usage."},
-                        {"value",  1. * kv_cache_used_cells / params.n_ctx}
-                },{
-                        {"name",  "kv_cache_tokens"},
-                        {"help",  "KV-cache tokens."},
-                        {"value",  (uint64_t) data["kv_cache_tokens_count"]}
-                },{
-                        {"name",  "requests_processing"},
-                        {"help",  "Number of request processing."},
-                        {"value",  (uint64_t) data["processing"]}
-                },{
-                        {"name",  "requests_deferred"},
-                        {"help",  "Number of request deferred."},
-                        {"value",  (uint64_t) data["deferred"]}
-                }}}
-            };
-
-            std::stringstream prometheus;
-
-            for (const auto & el : all_metrics_def.items()) {
-                const auto & type        = el.key();
-                const auto & metrics_def = el.value();
-
-                for (const auto & metric_def : metrics_def) {
-                    const std::string name = metric_def["name"];
-                    const std::string help = metric_def["help"];
-
-                    auto value = json_value(metric_def, "value", 0.);
-                    prometheus << "# HELP llamacpp:" << name << " " << help  << "\n"
-                               << "# TYPE llamacpp:" << name << " " << type  << "\n"
-                               << "llamacpp:"        << name << " " << value << "\n";
-                }
-            }
-
-            const int64_t t_start = data["t_start"];
-            res.set_header("Process-Start-Time-Unix", std::to_string(t_start));
-
-            res.set_content(prometheus.str(), "text/plain; version=0.0.4");
-            res.status = 200; // HTTP OK
-        });
-    }
-
-    svr.set_logger(log_server_request);
-
-    svr.set_exception_handler([](const httplib::Request &, httplib::Response & res, std::exception_ptr ep) {
-        const char fmt[] = "500 Internal Server Error\n%s";
-
-        char buf[BUFSIZ];
-        try {
-            std::rethrow_exception(std::move(ep));
-        } catch (std::exception &e) {
-            snprintf(buf, sizeof(buf), fmt, e.what());
-        } catch (...) {
-            snprintf(buf, sizeof(buf), fmt, "Unknown Exception");
-        }
-
-        res.set_content(buf, "text/plain; charset=utf-8");
-        res.status = 500;
-    });
-
-    svr.set_error_handler([](const httplib::Request &, httplib::Response & res) {
-        if (res.status == 401) {
-            res.set_content("Unauthorized", "text/plain; charset=utf-8");
-        }
-        if (res.status == 400) {
-            res.set_content("Invalid request", "text/plain; charset=utf-8");
-        }
-        if (res.status == 404) {
-            res.set_content("File Not Found", "text/plain; charset=utf-8");
-        }
-    });
-
-    // set timeouts and change hostname and port
-    svr.set_read_timeout (sparams.read_timeout);
-    svr.set_write_timeout(sparams.write_timeout);
-
-    if (!svr.bind_to_port(sparams.hostname, sparams.port)) {
-        fprintf(stderr, "\ncouldn't bind to server socket: hostname=%s port=%d\n\n", sparams.hostname.c_str(), sparams.port);
-        return 1;
-    }
-
-    // Set the base directory for serving static files
-    svr.set_base_dir(sparams.public_path);
-
-    std::unordered_map<std::string, std::string> log_data;
-
-    log_data["hostname"] = sparams.hostname;
-    log_data["port"]     = std::to_string(sparams.port);
-
-    if (sparams.api_keys.size() == 1) {
-        log_data["api_key"] = "api_key: ****" + sparams.api_keys[0].substr(sparams.api_keys[0].length() - 4);
-    } else if (sparams.api_keys.size() > 1) {
-        log_data["api_key"] = "api_key: " + std::to_string(sparams.api_keys.size()) + " keys loaded";
-    }
-
-    // load the model
-    if (!ctx_server.load_model(params)) {
-        state.store(SERVER_STATE_ERROR);
-        return 1;
-    } else {
-        ctx_server.initialize();
-        state.store(SERVER_STATE_READY);
-    }
-
-    LOG_INFO("model loaded", {});
-
-    const auto model_meta = ctx_server.model_meta();
-
-    if (sparams.chat_template.empty()) { // custom chat template is not supplied
-        if (!ctx_server.validate_model_chat_template()) {
-            LOG_ERROR("The chat template that comes with this model is not yet supported, falling back to chatml. This may cause the model to output suboptimal responses", {});
-            sparams.chat_template = "chatml";
-        }
-    }
-
-    // Middleware for API key validation
-    auto validate_api_key = [&sparams](const httplib::Request &req, httplib::Response &res) -> bool {
-        // If API key is not set, skip validation
-        if (sparams.api_keys.empty()) {
-            return true;
-        }
-
-        // Check for API key in the header
-        auto auth_header = req.get_header_value("Authorization");
-
-        std::string prefix = "Bearer ";
-        if (auth_header.substr(0, prefix.size()) == prefix) {
-            std::string received_api_key = auth_header.substr(prefix.size());
-            if (std::find(sparams.api_keys.begin(), sparams.api_keys.end(), received_api_key) != sparams.api_keys.end()) {
-                return true; // API key is valid
-            }
-        }
-
-        // API key is invalid or not provided
-        res.set_content("Unauthorized: Invalid API Key", "text/plain; charset=utf-8");
-        res.status = 401; // Unauthorized
-
-        LOG_WARNING("Unauthorized: Invalid API Key", {});
-
-        return false;
     };
 
-    // this is only called if no index.html is found in the public --path
-    svr.Get("/", [](const httplib::Request &, httplib::Response & res) {
-        res.set_content(reinterpret_cast<const char*>(&index_html), index_html_len, "text/html; charset=utf-8");
-        return false;
-    });
+    const auto handle_slots = [&](const httplib::Request &, httplib::Response & res) {
+        if (!sparams.slots_endpoint) {
+            res_error(res, format_error_response("This server does not support slots endpoint.", ERROR_TYPE_NOT_SUPPORTED));
+            return;
+        }
 
-    // this is only called if no index.js is found in the public --path
-    svr.Get("/index.js", [](const httplib::Request &, httplib::Response & res) {
-        res.set_content(reinterpret_cast<const char *>(&index_js), index_js_len, "text/javascript; charset=utf-8");
-        return false;
-    });
+        // request slots data using task queue
+        server_task task;
+        task.id = ctx_server.queue_tasks.get_new_id();
+        task.id_multi  = -1;
+        task.id_target = -1;
+        task.type = SERVER_TASK_TYPE_METRICS;
 
-    // this is only called if no index.html is found in the public --path
-    svr.Get("/completion.js", [](const httplib::Request &, httplib::Response & res) {
-        res.set_content(reinterpret_cast<const char*>(&completion_js), completion_js_len, "application/javascript; charset=utf-8");
-        return false;
-    });
+        ctx_server.queue_results.add_waiting_task_id(task.id);
+        ctx_server.queue_tasks.post(task);
 
-    // this is only called if no index.html is found in the public --path
-    svr.Get("/json-schema-to-grammar.mjs", [](const httplib::Request &, httplib::Response & res) {
-        res.set_content(reinterpret_cast<const char*>(&json_schema_to_grammar_mjs), json_schema_to_grammar_mjs_len, "application/javascript; charset=utf-8");
-        return false;
-    });
+        // get the result
+        server_task_result result = ctx_server.queue_results.recv(task.id);
+        ctx_server.queue_results.remove_waiting_task_id(task.id);
 
-    svr.Get("/props", [&ctx_server](const httplib::Request & req, httplib::Response & res) {
+        res.set_content(result.data["slots"].dump(), "application/json");
+        res.status = 200; // HTTP OK
+    };
+
+    const auto handle_metrics = [&](const httplib::Request &, httplib::Response & res) {
+        if (!sparams.metrics_endpoint) {
+            res_error(res, format_error_response("This server does not support metrics endpoint.", ERROR_TYPE_NOT_SUPPORTED));
+            return;
+        }
+
+        // request slots data using task queue
+        server_task task;
+        task.id = ctx_server.queue_tasks.get_new_id();
+        task.id_multi  = -1;
+        task.id_target = -1;
+        task.type = SERVER_TASK_TYPE_METRICS;
+        task.data.push_back({{"reset_bucket", true}});
+
+        ctx_server.queue_results.add_waiting_task_id(task.id);
+        ctx_server.queue_tasks.post(task);
+
+        // get the result
+        server_task_result result = ctx_server.queue_results.recv(task.id);
+        ctx_server.queue_results.remove_waiting_task_id(task.id);
+
+        json data = result.data;
+
+        const uint64_t n_prompt_tokens_processed = data["n_prompt_tokens_processed"];
+        const uint64_t t_prompt_processing       = data["t_prompt_processing"];
+
+        const uint64_t n_tokens_predicted  = data["n_tokens_predicted"];
+        const uint64_t t_tokens_generation = data["t_tokens_generation"];
+
+        const int32_t kv_cache_used_cells = data["kv_cache_used_cells"];
+
+        // metrics definition: https://prometheus.io/docs/practices/naming/#metric-names
+        json all_metrics_def = json {
+            {"counter", {{
+                    {"name",  "prompt_tokens_total"},
+                    {"help",  "Number of prompt tokens processed."},
+                    {"value",  (uint64_t) data["n_prompt_tokens_processed_total"]}
+            }, {
+                    {"name",  "prompt_seconds_total"},
+                    {"help",  "Prompt process time"},
+                    {"value",  (uint64_t) data["t_prompt_processing_total"] / 1.e3}
+            }, {
+                    {"name",  "tokens_predicted_total"},
+                    {"help",  "Number of generation tokens processed."},
+                    {"value",  (uint64_t) data["n_tokens_predicted_total"]}
+            }, {
+                    {"name",  "tokens_predicted_seconds_total"},
+                    {"help",  "Predict process time"},
+                    {"value",  (uint64_t) data["t_tokens_generation_total"] / 1.e3}
+            }}},
+            {"gauge", {{
+                    {"name",  "prompt_tokens_seconds"},
+                    {"help",  "Average prompt throughput in tokens/s."},
+                    {"value",  n_prompt_tokens_processed ? 1.e3 / t_prompt_processing * n_prompt_tokens_processed : 0.}
+            },{
+                    {"name",  "predicted_tokens_seconds"},
+                    {"help",  "Average generation throughput in tokens/s."},
+                    {"value",  n_tokens_predicted ? 1.e3 / t_tokens_generation * n_tokens_predicted : 0.}
+            },{
+                    {"name",  "kv_cache_usage_ratio"},
+                    {"help",  "KV-cache usage. 1 means 100 percent usage."},
+                    {"value",  1. * kv_cache_used_cells / params.n_ctx}
+            },{
+                    {"name",  "kv_cache_tokens"},
+                    {"help",  "KV-cache tokens."},
+                    {"value",  (uint64_t) data["kv_cache_tokens_count"]}
+            },{
+                    {"name",  "requests_processing"},
+                    {"help",  "Number of request processing."},
+                    {"value",  (uint64_t) data["processing"]}
+            },{
+                    {"name",  "requests_deferred"},
+                    {"help",  "Number of request deferred."},
+                    {"value",  (uint64_t) data["deferred"]}
+            }}}
+        };
+
+        std::stringstream prometheus;
+
+        for (const auto & el : all_metrics_def.items()) {
+            const auto & type        = el.key();
+            const auto & metrics_def = el.value();
+
+            for (const auto & metric_def : metrics_def) {
+                const std::string name = metric_def["name"];
+                const std::string help = metric_def["help"];
+
+                auto value = json_value(metric_def, "value", 0.);
+                prometheus << "# HELP llamacpp:" << name << " " << help  << "\n"
+                            << "# TYPE llamacpp:" << name << " " << type  << "\n"
+                            << "llamacpp:"        << name << " " << value << "\n";
+            }
+        }
+
+        const int64_t t_start = data["t_start"];
+        res.set_header("Process-Start-Time-Unix", std::to_string(t_start));
+
+        res.set_content(prometheus.str(), "text/plain; version=0.0.4");
+        res.status = 200; // HTTP OK
+    };
+
+    const auto handle_props = [&ctx_server](const httplib::Request & req, httplib::Response & res) {
         res.set_header("Access-Control-Allow-Origin", req.get_header_value("Origin"));
         json data = {
             { "user_name",                   ctx_server.name_user.c_str() },
@@ -2966,13 +3106,10 @@ int main(int argc, char ** argv) {
         };
 
         res.set_content(data.dump(), "application/json; charset=utf-8");
-    });
+    };
 
-    const auto completions = [&ctx_server, &validate_api_key](const httplib::Request & req, httplib::Response & res) {
+    const auto handle_completions = [&ctx_server, &res_error](const httplib::Request & req, httplib::Response & res) {
         res.set_header("Access-Control-Allow-Origin", req.get_header_value("Origin"));
-        if (!validate_api_key(req, res)) {
-            return;
-        }
 
         json data = json::parse(req.body);
 
@@ -2986,8 +3123,7 @@ int main(int argc, char ** argv) {
             if (!result.error && result.stop) {
                 res.set_content(result.data.dump(-1, ' ', false, json::error_handler_t::replace), "application/json; charset=utf-8");
             } else {
-                res.status = 500;
-                res.set_content(result.data["content"], "text/plain; charset=utf-8");
+                res_error(res, result.data);
             }
 
             ctx_server.queue_results.remove_waiting_task_id(id_task);
@@ -3048,11 +3184,7 @@ int main(int argc, char ** argv) {
         }
     };
 
-    svr.Post("/completion", completions); // legacy
-    svr.Post("/completions", completions);
-    svr.Post("/v1/completions", completions);
-
-    svr.Get("/v1/models", [&params, &model_meta](const httplib::Request & req, httplib::Response & res) {
+    const auto handle_models = [&params, &model_meta](const httplib::Request & req, httplib::Response & res) {
         res.set_header("Access-Control-Allow-Origin", req.get_header_value("Origin"));
 
         json models = {
@@ -3069,14 +3201,10 @@ int main(int argc, char ** argv) {
         };
 
         res.set_content(models.dump(), "application/json; charset=utf-8");
-    });
+    };
 
-    const auto chat_completions = [&ctx_server, &validate_api_key, &sparams](const httplib::Request & req, httplib::Response & res) {
+    const auto handle_chat_completions = [&ctx_server, &sparams, &res_error](const httplib::Request & req, httplib::Response & res) {
         res.set_header("Access-Control-Allow-Origin", req.get_header_value("Origin"));
-        if (!validate_api_key(req, res)) {
-            return;
-        }
-
         json data = oaicompat_completion_params_parse(ctx_server.model, json::parse(req.body), sparams.chat_template);
 
         const int id_task = ctx_server.queue_tasks.get_new_id();
@@ -3084,24 +3212,24 @@ int main(int argc, char ** argv) {
         ctx_server.queue_results.add_waiting_task_id(id_task);
         ctx_server.request_completion(id_task, -1, data, false, false);
 
+        const auto completion_id = gen_chatcmplid();
         if (!json_value(data, "stream", false)) {
             server_task_result result = ctx_server.queue_results.recv(id_task);
 
             if (!result.error && result.stop) {
-                json result_oai = format_final_response_oaicompat(data, result.data);
+                json result_oai = format_final_response_oaicompat(data, result.data, completion_id);
 
                 res.set_content(result_oai.dump(-1, ' ', false, json::error_handler_t::replace), "application/json; charset=utf-8");
             } else {
-                res.status = 500;
-                res.set_content(result.data["content"], "text/plain; charset=utf-8");
+                res_error(res, result.data);
             }
             ctx_server.queue_results.remove_waiting_task_id(id_task);
         } else {
-            const auto chunked_content_provider = [id_task, &ctx_server](size_t, httplib::DataSink & sink) {
+            const auto chunked_content_provider = [id_task, &ctx_server, completion_id](size_t, httplib::DataSink & sink) {
                 while (true) {
                     server_task_result result = ctx_server.queue_results.recv(id_task);
                     if (!result.error) {
-                        std::vector<json> result_array = format_partial_response_oaicompat(result.data);
+                        std::vector<json> result_array = format_partial_response_oaicompat(result.data, completion_id);
 
                         for (auto it = result_array.begin(); it != result_array.end(); ++it) {
                             if (!it->empty()) {
@@ -3147,14 +3275,8 @@ int main(int argc, char ** argv) {
         }
     };
 
-    svr.Post("/chat/completions",    chat_completions);
-    svr.Post("/v1/chat/completions", chat_completions);
-
-    svr.Post("/infill", [&ctx_server, &validate_api_key](const httplib::Request & req, httplib::Response & res) {
+    const auto handle_infill = [&ctx_server, &res_error](const httplib::Request & req, httplib::Response & res) {
         res.set_header("Access-Control-Allow-Origin", req.get_header_value("Origin"));
-        if (!validate_api_key(req, res)) {
-            return;
-        }
 
         json data = json::parse(req.body);
 
@@ -3168,8 +3290,7 @@ int main(int argc, char ** argv) {
             if (!result.error && result.stop) {
                 res.set_content(result.data.dump(-1, ' ', false, json::error_handler_t::replace), "application/json; charset=utf-8");
             } else {
-                res.status = 404;
-                res.set_content(result.data["content"], "text/plain; charset=utf-8");
+                res_error(res, result.data);
             }
 
             ctx_server.queue_results.remove_waiting_task_id(id_task);
@@ -3212,13 +3333,9 @@ int main(int argc, char ** argv) {
 
             res.set_chunked_content_provider("text/event-stream", chunked_content_provider, on_complete);
         }
-    });
+    };
 
-    svr.Options(R"(/.*)", [](const httplib::Request &, httplib::Response & res) {
-        return res.set_content("", "application/json; charset=utf-8");
-    });
-
-    svr.Post("/tokenize", [&ctx_server](const httplib::Request & req, httplib::Response & res) {
+    const auto handle_tokenize = [&ctx_server](const httplib::Request & req, httplib::Response & res) {
         res.set_header("Access-Control-Allow-Origin", req.get_header_value("Origin"));
         const json body = json::parse(req.body);
 
@@ -3228,9 +3345,9 @@ int main(int argc, char ** argv) {
         }
         const json data = format_tokenizer_response(tokens);
         return res.set_content(data.dump(), "application/json; charset=utf-8");
-    });
+    };
 
-    svr.Post("/detokenize", [&ctx_server](const httplib::Request & req, httplib::Response & res) {
+    const auto handle_detokenize = [&ctx_server](const httplib::Request & req, httplib::Response & res) {
         res.set_header("Access-Control-Allow-Origin", req.get_header_value("Origin"));
         const json body = json::parse(req.body);
 
@@ -3242,9 +3359,9 @@ int main(int argc, char ** argv) {
 
         const json data = format_detokenized_response(content);
         return res.set_content(data.dump(), "application/json; charset=utf-8");
-    });
+    };
 
-    svr.Post("/embedding", [&params, &ctx_server](const httplib::Request & req, httplib::Response & res) {
+    const auto handle_embeddings = [&params, &ctx_server, &res_error](const httplib::Request & req, httplib::Response & res) {
         res.set_header("Access-Control-Allow-Origin", req.get_header_value("Origin"));
         if (!params.embedding) {
             res.status = 501;
@@ -3253,106 +3370,133 @@ int main(int argc, char ** argv) {
         }
 
         const json body = json::parse(req.body);
+        bool is_openai = false;
 
-        json prompt;
-        if (body.count("content") != 0) {
-            prompt = body["content"];
-        } else {
-            prompt = "";
-        }
-
-        // create and queue the task
-        const int id_task = ctx_server.queue_tasks.get_new_id();
-
-        ctx_server.queue_results.add_waiting_task_id(id_task);
-        ctx_server.request_completion(id_task, -1, { {"prompt", prompt}, { "n_predict", 0} }, false, true);
-
-        // get the result
-        server_task_result result = ctx_server.queue_results.recv(id_task);
-        ctx_server.queue_results.remove_waiting_task_id(id_task);
-
-        // send the result
-        return res.set_content(result.data.dump(), "application/json; charset=utf-8");
-    });
-
-    svr.Post("/v1/embeddings", [&params, &ctx_server](const httplib::Request & req, httplib::Response & res) {
-        res.set_header("Access-Control-Allow-Origin", req.get_header_value("Origin"));
-        if (!params.embedding) {
-            res.status = 501;
-            res.set_content("This server does not support embeddings. Start it with `--embeddings`", "text/plain; charset=utf-8");
-            return;
-        }
-
-        const json body = json::parse(req.body);
-
-        json prompt;
+        // an input prompt can string or a list of tokens (integer)
+        std::vector<json> prompts;
         if (body.count("input") != 0) {
-            prompt = body["input"];
-            if (prompt.is_array()) {
-                json data = json::array();
-
-                int i = 0;
-                for (const json & elem : prompt) {
-                    const int id_task = ctx_server.queue_tasks.get_new_id();
-
-                    ctx_server.queue_results.add_waiting_task_id(id_task);
-                    ctx_server.request_completion(id_task, -1, { {"prompt", elem}, { "n_predict", 0} }, false, true);
-
-                    // get the result
-                    server_task_result result = ctx_server.queue_results.recv(id_task);
-                    ctx_server.queue_results.remove_waiting_task_id(id_task);
-
-                    json embedding = json{
-                        {"embedding", json_value(result.data, "embedding", json::array())},
-                        {"index",     i++},
-                        {"object",    "embedding"}
-                    };
-
-                    data.push_back(embedding);
+            is_openai = true;
+            if (body["input"].is_array()) {
+                // support multiple prompts
+                for (const json & elem : body["input"]) {
+                    prompts.push_back(elem);
                 }
-
-                json result = format_embeddings_response_oaicompat(body, data);
-
-                return res.set_content(result.dump(), "application/json; charset=utf-8");
+            } else {
+                // single input prompt
+                prompts.push_back(body["input"]);
             }
+        } else if (body.count("content") != 0) {
+            // only support single prompt here
+            std::string content = body["content"];
+            prompts.push_back(content);
         } else {
-            prompt = "";
+            res_error(res, format_error_response("\"input\" or \"content\" must be provided", ERROR_TYPE_INVALID_REQUEST));
+            return;
         }
 
-        // create and queue the task
-        const int id_task = ctx_server.queue_tasks.get_new_id();
+        // process all prompts
+        json responses = json::array();
+        for (auto & prompt : prompts) {
+            // TODO @ngxson : maybe support multitask for this endpoint?
+            // create and queue the task
+            const int id_task = ctx_server.queue_tasks.get_new_id();
 
-        ctx_server.queue_results.add_waiting_task_id(id_task);
-        ctx_server.request_completion(id_task, -1, { {"prompt", prompt}, { "n_predict", 0}}, false, true);
+            ctx_server.queue_results.add_waiting_task_id(id_task);
+            ctx_server.request_completion(id_task, -1, { {"prompt", prompt}, { "n_predict", 0}}, false, true);
 
-        // get the result
-        server_task_result result = ctx_server.queue_results.recv(id_task);
-        ctx_server.queue_results.remove_waiting_task_id(id_task);
-
-        json data = json::array({json{
-            {"embedding", json_value(result.data, "embedding", json::array())},
-            {"index",     0},
-            {"object",    "embedding"}
-        }}
-        );
-
-        json root = format_embeddings_response_oaicompat(body, data);
+            // get the result
+            server_task_result result = ctx_server.queue_results.recv(id_task);
+            ctx_server.queue_results.remove_waiting_task_id(id_task);
+            if (!result.error) {
+                // append to the responses
+                responses.push_back(result.data);
+            } else {
+                // error received, ignore everything else
+                res_error(res, result.data);
+                return;
+            }
+        }
 
+        // write JSON response
+        json root;
+        if (is_openai) {
+            json res_oai = json::array();
+            int i = 0;
+            for (auto & elem : responses) {
+                res_oai.push_back(json{
+                    {"embedding", json_value(elem, "embedding", json::array())},
+                    {"index",     i++},
+                    {"object",    "embedding"}
+                });
+            }
+            root = format_embeddings_response_oaicompat(body, res_oai);
+        } else {
+            root = responses[0];
+        }
         return res.set_content(root.dump(), "application/json; charset=utf-8");
-    });
+    };
 
+    //
+    // Router
+    //
+
+    // register static assets routes
+    if (!sparams.public_path.empty()) {
+        // Set the base directory for serving static files
+        svr->set_base_dir(sparams.public_path);
+    }
+
+    // using embedded static files
+    auto handle_static_file = [](unsigned char * content, size_t len, const char * mime_type) {
+        return [content, len, mime_type](const httplib::Request &, httplib::Response & res) {
+            res.set_content(reinterpret_cast<const char*>(content), len, mime_type);
+            return false;
+        };
+    };
+
+    svr->Options(R"(/.*)", [](const httplib::Request &, httplib::Response & res) {
+        // TODO @ngxson : I have no idea what it is... maybe this is redundant?
+        return res.set_content("", "application/json; charset=utf-8");
+    });
+    svr->Get("/", handle_static_file(index_html, index_html_len, "text/html; charset=utf-8"));
+    svr->Get("/index.js", handle_static_file(index_js, index_js_len, "text/javascript; charset=utf-8"));
+    svr->Get("/completion.js", handle_static_file(completion_js, completion_js_len, "text/javascript; charset=utf-8"));
+    svr->Get("/json-schema-to-grammar.mjs", handle_static_file(
+        json_schema_to_grammar_mjs, json_schema_to_grammar_mjs_len, "text/javascript; charset=utf-8"));
+
+    // register API routes
+    svr->Get ("/health",              handle_health);
+    svr->Get ("/slots",               handle_slots);
+    svr->Get ("/metrics",             handle_metrics);
+    svr->Get ("/props",               handle_props);
+    svr->Get ("/v1/models",           handle_models);
+    svr->Post("/completion",          handle_completions); // legacy
+    svr->Post("/completions",         handle_completions);
+    svr->Post("/v1/completions",      handle_completions);
+    svr->Post("/chat/completions",    handle_chat_completions);
+    svr->Post("/v1/chat/completions", handle_chat_completions);
+    svr->Post("/infill",              handle_infill);
+    svr->Post("/embedding",           handle_embeddings); // legacy
+    svr->Post("/embeddings",          handle_embeddings);
+    svr->Post("/v1/embeddings",       handle_embeddings);
+    svr->Post("/tokenize",            handle_tokenize);
+    svr->Post("/detokenize",          handle_detokenize);
+
+    //
+    // Start the server
+    //
     if (sparams.n_threads_http < 1) {
         // +2 threads for monitoring endpoints
         sparams.n_threads_http = std::max(params.n_parallel + 2, (int32_t) std::thread::hardware_concurrency() - 1);
     }
     log_data["n_threads_http"] =  std::to_string(sparams.n_threads_http);
-    svr.new_task_queue = [&sparams] { return new httplib::ThreadPool(sparams.n_threads_http); };
+    svr->new_task_queue = [&sparams] { return new httplib::ThreadPool(sparams.n_threads_http); };
 
     LOG_INFO("HTTP server listening", log_data);
 
     // run the HTTP server in a thread - see comment below
     std::thread t([&]() {
-        if (!svr.listen_after_bind()) {
+        if (!svr->listen_after_bind()) {
             state.store(SERVER_STATE_ERROR);
             return 1;
         }
@@ -3364,7 +3508,7 @@ int main(int argc, char ** argv) {
         &server_context::process_single_task, &ctx_server, std::placeholders::_1));
     ctx_server.queue_tasks.on_finish_multitask(std::bind(
         &server_context::on_finish_multitask, &ctx_server, std::placeholders::_1));
-    ctx_server.queue_tasks.on_run_slots(std::bind(
+    ctx_server.queue_tasks.on_update_slots(std::bind(
         &server_context::update_slots, &ctx_server));
     ctx_server.queue_results.on_multitask_update(std::bind(
         &server_queue::update_multitask,
@@ -3393,7 +3537,7 @@ int main(int argc, char ** argv) {
 
     ctx_server.queue_tasks.start_loop();
 
-    svr.stop();
+    svr->stop();
     t.join();
 
     llama_backend_free();
diff --git a/examples/server/tests/features/environment.py b/examples/server/tests/features/environment.py
index 9fd330db6..8ad987e1b 100644
--- a/examples/server/tests/features/environment.py
+++ b/examples/server/tests/features/environment.py
@@ -1,9 +1,10 @@
+import errno
 import os
 import socket
 import subprocess
 import time
 from contextlib import closing
-from signal import SIGKILL
+import signal
 
 
 def before_scenario(context, scenario):
@@ -29,44 +30,71 @@ def after_scenario(context, scenario):
                     for line in f:
                         print(line)
         if not is_server_listening(context.server_fqdn, context.server_port):
-            print("\x1b[33;101mERROR: Server stopped listening\x1b[0m")
+            print("\x1b[33;101mERROR: Server stopped listening\x1b[0m\n")
 
     if not pid_exists(context.server_process.pid):
         assert False, f"Server not running pid={context.server_process.pid} ..."
 
-    print(f"stopping server pid={context.server_process.pid} ...")
-    context.server_process.kill()
+    server_graceful_shutdown(context)
+
     # Wait few for socket to free up
     time.sleep(0.05)
 
     attempts = 0
-    while is_server_listening(context.server_fqdn, context.server_port):
-        print(f"stopping server pid={context.server_process.pid} ...")
-        os.kill(context.server_process.pid, SIGKILL)
+    while pid_exists(context.server_process.pid) or is_server_listening(context.server_fqdn, context.server_port):
+        server_kill(context)
         time.sleep(0.1)
         attempts += 1
         if attempts > 5:
-            print(f"Server dangling exits, killing all {context.server_path} ...")
-            process = subprocess.run(['killall', '-9', context.server_path],
-                                     stderr=subprocess.PIPE,
-                                     universal_newlines=True)
-            print(process)
+            server_kill_hard(context)
+
+
+def server_graceful_shutdown(context):
+    print(f"shutting down server pid={context.server_process.pid} ...\n")
+    if os.name == 'nt':
+        os.kill(context.server_process.pid, signal.CTRL_C_EVENT)
+    else:
+        os.kill(context.server_process.pid, signal.SIGINT)
+
+
+def server_kill(context):
+    print(f"killing server pid={context.server_process.pid} ...\n")
+    context.server_process.kill()
+
+
+def server_kill_hard(context):
+    pid = context.server_process.pid
+    path = context.server_path
+
+    print(f"Server dangling exits, hard killing force {pid}={path}...\n")
+    if os.name == 'nt':
+        process = subprocess.check_output(['taskkill', '/F', '/pid', str(pid)]).decode()
+        print(process)
+    else:
+        os.kill(-pid, signal.SIGKILL)
 
 
 def is_server_listening(server_fqdn, server_port):
     with closing(socket.socket(socket.AF_INET, socket.SOCK_STREAM)) as sock:
         result = sock.connect_ex((server_fqdn, server_port))
-        return result == 0
+        _is_server_listening = result == 0
+        if _is_server_listening:
+            print(f"server is listening on {server_fqdn}:{server_port}...\n")
+        return _is_server_listening
 
 
 def pid_exists(pid):
     """Check whether pid exists in the current process table."""
-    import errno
     if pid < 0:
         return False
-    try:
-        os.kill(pid, 0)
-    except OSError as e:
-        return e.errno == errno.EPERM
+    if os.name == 'nt':
+        output = subprocess.check_output(['TASKLIST', '/FI', f'pid eq {pid}']).decode()
+        print(output)
+        return "No tasks are running" not in output
     else:
-        return True
+        try:
+            os.kill(pid, 0)
+        except OSError as e:
+            return e.errno == errno.EPERM
+        else:
+            return True
diff --git a/examples/server/tests/features/parallel.feature b/examples/server/tests/features/parallel.feature
index 066698c8e..a66fed626 100644
--- a/examples/server/tests/features/parallel.feature
+++ b/examples/server/tests/features/parallel.feature
@@ -6,8 +6,8 @@ Feature: Parallel
     Given a server listening on localhost:8080
     And   a model file tinyllamas/stories260K.gguf from HF repo ggml-org/models
     And   42 as server seed
-    And   512 as batch size
-    And   64 KV cache size
+    And   128 as batch size
+    And   256 KV cache size
     And   2 slots
     And   continuous batching
     Then  the server is starting
@@ -76,6 +76,7 @@ Feature: Parallel
       | disabled  | 128       |
       | enabled   | 64        |
 
+
   Scenario:  Multi users with total number of tokens to predict exceeds the KV Cache size #3969
     Given a prompt:
       """
diff --git a/examples/server/tests/features/security.feature b/examples/server/tests/features/security.feature
index 42a6709a5..1d6aa40ea 100644
--- a/examples/server/tests/features/security.feature
+++ b/examples/server/tests/features/security.feature
@@ -39,8 +39,9 @@ Feature: Security
 
 
   Scenario Outline: CORS Options
-    When an OPTIONS request is sent from <origin>
-    Then CORS header <cors_header> is set to <cors_header_value>
+    Given a user api key llama.cpp
+    When  an OPTIONS request is sent from <origin>
+    Then  CORS header <cors_header> is set to <cors_header_value>
 
     Examples: Headers
       | origin          | cors_header                      | cors_header_value |
diff --git a/examples/server/tests/features/server.feature b/examples/server/tests/features/server.feature
index 878ac1363..5014f326d 100644
--- a/examples/server/tests/features/server.feature
+++ b/examples/server/tests/features/server.feature
@@ -10,11 +10,10 @@ Feature: llama.cpp server
       # KV Cache corresponds to the total amount of tokens
       # that can be stored across all independent sequences: #4130
       # see --ctx-size and #5568
-    And   32 KV cache size
-    And   512 as batch size
-    And   1 slots
-    And   embeddings extraction
-    And   32 server max tokens to predict
+    And   256 KV cache size
+    And   32 as batch size
+    And   2 slots
+    And   64 server max tokens to predict
     And   prometheus compatible metrics exposed
     Then  the server is starting
     Then  the server is healthy
@@ -23,18 +22,35 @@ Feature: llama.cpp server
     Then the server is ready
     And  all slots are idle
 
+
   Scenario Outline: Completion
     Given a prompt <prompt>
     And   <n_predict> max tokens to predict
     And   a completion request with no api error
     Then  <n_predicted> tokens are predicted matching <re_content>
+    And   the completion is <truncated> truncated
+    And   <n_prompt> prompt tokens are processed
     And   prometheus metrics are exposed
     And   metric llamacpp:tokens_predicted is <n_predicted>
 
     Examples: Prompts
-      | prompt                           | n_predict | re_content                       | n_predicted |
-      | I believe the meaning of life is | 8         | (read\|going)+                   | 8           |
-      | Write a joke about AI            | 64        | (park\|friends\|scared\|always)+ | 32          |
+      | prompt                                                                    | n_predict | re_content                    | n_prompt | n_predicted | truncated |
+      | I believe the meaning of life is                                          | 8         | (read\|going)+                | 18       | 8           | not       |
+      | Write a joke about AI from a very long prompt which will not be truncated | 256       | (princesses\|everyone\|kids)+ | 46       | 64          | not       |
+
+  Scenario: Completion prompt truncated
+    Given a prompt:
+    """
+    Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.
+    Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat.
+    Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur.
+    Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.
+    """
+    And   a completion request with no api error
+    Then  64 tokens are predicted matching fun|Annaks|popcorns|pictry
+    And   the completion is  truncated
+    And   109 prompt tokens are processed
+
 
   Scenario Outline: OAI Compatibility
     Given a model <model>
@@ -44,11 +60,14 @@ Feature: llama.cpp server
     And   streaming is <enable_streaming>
     Given an OAI compatible chat completions request with no api error
     Then  <n_predicted> tokens are predicted matching <re_content>
+    And   <n_prompt> prompt tokens are processed
+    And   the completion is <truncated> truncated
 
     Examples: Prompts
-      | model        | system_prompt               | user_prompt                          | max_tokens | re_content             | n_predicted | enable_streaming |
-      | llama-2      | Book                        | What is the best book                | 8          | (Mom\|what)+           | 8           | disabled         |
-      | codellama70b | You are a coding assistant. | Write the fibonacci function in c++. | 64         | (thanks\|happy\|bird)+ | 32          | enabled          |
+      | model        | system_prompt               | user_prompt                          | max_tokens | re_content             | n_prompt | n_predicted | enable_streaming | truncated |
+      | llama-2      | Book                        | What is the best book                | 8          | (Here\|what)+          | 77       | 8           | disabled         | not       |
+      | codellama70b | You are a coding assistant. | Write the fibonacci function in c++. | 128        | (thanks\|happy\|bird)+ | -1       | 64          | enabled          |           |
+
 
   Scenario: Tokenize / Detokenize
     When tokenizing:
diff --git a/examples/server/tests/features/steps/steps.py b/examples/server/tests/features/steps/steps.py
index d7f005836..98c2b6174 100644
--- a/examples/server/tests/features/steps/steps.py
+++ b/examples/server/tests/features/steps/steps.py
@@ -18,7 +18,7 @@ from huggingface_hub import hf_hub_download
 from prometheus_client import parser
 
 
-@step(u"a server listening on {server_fqdn}:{server_port}")
+@step("a server listening on {server_fqdn}:{server_port}")
 def step_server_config(context, server_fqdn, server_port):
     context.server_fqdn = server_fqdn
     context.server_port = int(server_port)
@@ -57,24 +57,24 @@ def step_server_config(context, server_fqdn, server_port):
     context.prompts = []
 
 
-@step(u'a model file {hf_file} from HF repo {hf_repo}')
+@step('a model file {hf_file} from HF repo {hf_repo}')
 def step_download_hf_model(context, hf_file, hf_repo):
     context.model_file = hf_hub_download(repo_id=hf_repo, filename=hf_file)
     if context.debug:
         print(f"model file: {context.model_file}\n")
 
 
-@step(u'a model alias {model_alias}')
+@step('a model alias {model_alias}')
 def step_model_alias(context, model_alias):
     context.model_alias = model_alias
 
 
-@step(u'{seed:d} as server seed')
+@step('{seed:d} as server seed')
 def step_seed(context, seed):
     context.server_seed = seed
 
 
-@step(u'{ngl:d} GPU offloaded layers')
+@step('{ngl:d} GPU offloaded layers')
 def step_n_gpu_layer(context, ngl):
     if 'N_GPU_LAYERS' in os.environ:
         new_ngl = int(os.environ['N_GPU_LAYERS'])
@@ -84,37 +84,37 @@ def step_n_gpu_layer(context, ngl):
     context.n_gpu_layer = ngl
 
 
-@step(u'{n_ctx:d} KV cache size')
+@step('{n_ctx:d} KV cache size')
 def step_n_ctx(context, n_ctx):
     context.n_ctx = n_ctx
 
 
-@step(u'{n_slots:d} slots')
+@step('{n_slots:d} slots')
 def step_n_slots(context, n_slots):
     context.n_slots = n_slots
 
 
-@step(u'{n_predict:d} server max tokens to predict')
+@step('{n_predict:d} server max tokens to predict')
 def step_server_n_predict(context, n_predict):
     context.n_server_predict = n_predict
 
 
-@step(u'continuous batching')
+@step('continuous batching')
 def step_server_continuous_batching(context):
     context.server_continuous_batching = True
 
 
-@step(u'embeddings extraction')
+@step('embeddings extraction')
 def step_server_embeddings(context):
     context.server_embeddings = True
 
 
-@step(u'prometheus compatible metrics exposed')
+@step('prometheus compatible metrics exposed')
 def step_server_metrics(context):
     context.server_metrics = True
 
 
-@step(u"the server is starting")
+@step("the server is starting")
 def step_start_server(context):
     start_server_background(context)
     attempts = 0
@@ -131,7 +131,7 @@ def step_start_server(context):
             time.sleep(0.1)
 
 
-@step(u"the server is {expecting_status}")
+@step("the server is {expecting_status}")
 @async_run_until_complete
 async def step_wait_for_the_server_to_be_started(context, expecting_status):
     match expecting_status:
@@ -160,7 +160,7 @@ async def step_wait_for_the_server_to_be_started(context, expecting_status):
             assert False, "unknown status"
 
 
-@step(u'all slots are {expected_slot_status_string}')
+@step('all slots are {expected_slot_status_string}')
 @async_run_until_complete
 async def step_all_slots_status(context, expected_slot_status_string):
     match expected_slot_status_string:
@@ -176,7 +176,7 @@ async def step_all_slots_status(context, expected_slot_status_string):
     await request_slots_status(context, expected_slots)
 
 
-@step(u'a completion request with {api_error} api error')
+@step('a completion request with {api_error} api error')
 @async_run_until_complete
 async def step_request_completion(context, api_error):
     expect_api_error = api_error == 'raised'
@@ -194,115 +194,133 @@ async def step_request_completion(context, api_error):
         assert completion == 401, f"completion must be an 401 status code: {completion}"
 
 
-@step(u'{predicted_n:d} tokens are predicted matching {re_content}')
+@step('{predicted_n:d} tokens are predicted matching {re_content}')
 def step_n_tokens_predicted_with_content(context, predicted_n, re_content):
-    assert_n_tokens_predicted(context.tasks_result.pop(), predicted_n, re_content)
+    context.completion = context.tasks_result.pop()
+    assert_n_tokens_predicted(context.completion, predicted_n, re_content)
 
 
-@step(u'{predicted_n:d} tokens are predicted')
+@step('{predicted_n:d} tokens are predicted')
 def step_n_tokens_predicted(context, predicted_n):
-    assert_n_tokens_predicted(context.tasks_result.pop(), predicted_n)
+    context.completion = context.tasks_result.pop()
+    assert_n_tokens_predicted(context.completion, predicted_n)
 
 
-@step(u'a user prompt {user_prompt}')
+@step('the completion is  truncated')
+def step_assert_completion_truncated(context):
+    step_assert_completion_truncated(context, '')
+
+
+@step('the completion is {truncated} truncated')
+def step_assert_completion_truncated(context, truncated):
+    truncated = truncated != "not"
+    assert context.completion['truncated'] == truncated, f'{context.completion}'
+
+
+@step('{n_prompt:d} prompt tokens are processed')
+def step_impl(context, n_prompt):
+    assert n_prompt < 0 or n_prompt == context.completion['timings']['prompt_n'], f"n_prompt={context.completion['timings']['prompt_n']}"
+
+
+@step('a user prompt {user_prompt}')
 def step_user_prompt(context, user_prompt):
     context.prompts.append(user_prompt)
     context.n_prompts = len(context.prompts)
 
 
-@step(u'a system prompt {system_prompt}')
+@step('a system prompt {system_prompt}')
 def step_system_prompt(context, system_prompt):
     context.system_prompt = system_prompt
 
 
-@step(u'a model {model}')
+@step('a model {model}')
 def step_model(context, model):
     context.model = model
 
 
-@step(u'{max_tokens:d} max tokens to predict')
+@step('{max_tokens:d} max tokens to predict')
 def step_max_tokens(context, max_tokens):
     context.n_predict = max_tokens
 
 
-@step(u'streaming is {enable_streaming}')
+@step('streaming is {enable_streaming}')
 def step_streaming(context, enable_streaming):
     context.enable_streaming = enable_streaming == 'enabled'
 
 
-@step(u'a user api key {user_api_key}')
+@step('a user api key {user_api_key}')
 def step_user_api_key(context, user_api_key):
     context.user_api_key = user_api_key
 
 
-@step(u'no user api key')
+@step('no user api key')
 def step_no_user_api_key(context):
     context.user_api_key = None
 
 
-@step(u'a user api key ')
+@step('a user api key ')
 def step_no_user_api_key_space(context):
     context.user_api_key = None
 
 
-@step(u'a server api key {server_api_key}')
+@step('a server api key {server_api_key}')
 def step_server_api_key(context, server_api_key):
     context.server_api_key = server_api_key
 
 
-@step(u'{n_junk:d} as number of junk')
+@step('{n_junk:d} as number of junk')
 def step_n_junk(context, n_junk):
     context.n_junk = n_junk
 
 
-@step(u'{n_batch:d} as batch size')
+@step('{n_batch:d} as batch size')
 def step_n_batch(context, n_batch):
     context.n_batch = n_batch
 
 
-@step(u'{seed:d} as seed')
+@step('{seed:d} as seed')
 def step_seed(context, seed):
     context.seed = seed
 
 
-@step(u'a prefix prompt')
+@step('a prefix prompt')
 def step_prompt_prefix(context):
-    context.prompt_prefix = context.text
+    context.prompt_prefix = context_text(context)
 
 
-@step(u'a junk suffix prompt')
+@step('a junk suffix prompt')
 def step_prompt_junk_suffix(context):
-    context.prompt_junk_suffix = context.text
+    context.prompt_junk_suffix = context_text(context)
 
 
-@step(u'a suffix prompt')
+@step('a suffix prompt')
 def step_prompt_suffix(context):
-    context.prompt_suffix = context.text
+    context.prompt_suffix = context_text(context)
 
 
-@step(u'{n_ga:d} group attention factor'
-      u' to extend context size through self-extend')
+@step('{n_ga:d} group attention factor'
+      ' to extend context size through self-extend')
 def step_impl(context, n_ga):
     context.n_ga = n_ga
 
 
-@step(u'{n_ga_w:d} group attention width to extend context size through self-extend')
+@step('{n_ga_w:d} group attention width to extend context size through self-extend')
 def step_impl(context, n_ga_w):
     context.n_ga_w = n_ga_w
 
 
-@step(u'a passkey prompt template')
+@step('a passkey prompt template')
 def step_prompt_passkey(context):
-    context.prompt_passkey = context.text
+    context.prompt_passkey = context_text(context)
 
 
-@step(u'{n_prompts:d} fixed prompts')
+@step('{n_prompts:d} fixed prompts')
 def step_fixed_prompts(context, n_prompts):
     context.prompts.extend([str(0)*(context.n_batch if context.n_batch is not None else 512) for i in range(n_prompts)])
     context.n_prompts = n_prompts
 
 
-@step(u'a "{passkey}" passkey challenge prompt with the passkey inserted every {i_pos:d} junk')
+@step('a "{passkey}" passkey challenge prompt with the passkey inserted every {i_pos:d} junk')
 def step_prompt_passkey(context, passkey, i_pos):
     prompt = ""
     for i in range(context.n_junk):
@@ -316,7 +334,7 @@ def step_prompt_passkey(context, passkey, i_pos):
     context.n_prompts = len(context.prompts)
 
 
-@step(u'an OAI compatible chat completions request with {api_error} api error')
+@step('an OAI compatible chat completions request with {api_error} api error')
 @async_run_until_complete
 async def step_oai_chat_completions(context, api_error):
     if context.debug:
@@ -351,19 +369,19 @@ async def step_oai_chat_completions(context, api_error):
         print(f"Completion response: {completion}")
 
 
-@step(u'a prompt')
+@step('a prompt')
 def step_a_prompt(context):
-    context.prompts.append(context.text)
+    context.prompts.append(context_text(context))
     context.n_prompts = len(context.prompts)
 
 
-@step(u'a prompt {prompt}')
+@step('a prompt {prompt}')
 def step_a_prompt_prompt(context, prompt):
     context.prompts.append(prompt)
     context.n_prompts = len(context.prompts)
 
 
-@step(u'concurrent completion requests')
+@step('concurrent completion requests')
 @async_run_until_complete()
 async def step_concurrent_completion_requests(context):
     await concurrent_requests(context,
@@ -379,7 +397,7 @@ async def step_concurrent_completion_requests(context):
                                                                            'user_api_key') else None)
 
 
-@step(u'concurrent OAI completions requests')
+@step('concurrent OAI completions requests')
 @async_run_until_complete
 async def step_oai_chat_completions(context):
     await concurrent_requests(context, oai_chat_completions,
@@ -399,7 +417,7 @@ async def step_oai_chat_completions(context):
                               if hasattr(context, 'user_api_key') else None)
 
 
-@step(u'concurrent OAI completions requests no v1')
+@step('concurrent OAI completions requests no v1')
 @async_run_until_complete
 async def step_oai_chat_completions(context):
     await concurrent_requests(context, oai_chat_completions,
@@ -422,13 +440,13 @@ async def step_oai_chat_completions(context):
                               if hasattr(context, 'user_api_key') else None)
 
 
-@step(u'all prompts are predicted')
+@step('all prompts are predicted')
 @async_run_until_complete
 async def step_all_prompts_are_predicted(context):
     await all_prompts_are_predicted(context)
 
 
-@step(u'all prompts are predicted with {n_expected_predicted:d} tokens')
+@step('all prompts are predicted with {n_expected_predicted:d} tokens')
 @async_run_until_complete
 async def step_all_prompts_are_predicted_with_n_tokens(context, n_expected_predicted):
     await all_prompts_are_predicted(context, n_expected_predicted)
@@ -442,14 +460,14 @@ async def all_prompts_are_predicted(context, expected_predicted_n=None):
     assert len(context.concurrent_tasks) == 0, f"{len(context.concurrent_tasks)} pending requests"
 
 
-@step(u'embeddings are computed for')
+@step('embeddings are computed for')
 @async_run_until_complete
 async def step_compute_embedding(context):
     context.n_prompts = 1
-    context.embeddings = await request_embedding(context.text, base_url=context.base_url)
+    context.embeddings = await request_embedding(context_text(context), base_url=context.base_url)
 
 
-@step(u'all embeddings are the same')
+@step('all embeddings are the same')
 @async_run_until_complete
 async def step_all_embeddings_are_the_same(context):
     n_embedding_requests = await gather_tasks_results(context)
@@ -473,7 +491,8 @@ async def step_all_embeddings_are_the_same(context):
                 print(f"{msg}\n")
             assert np.isclose(similarity, 1.0, rtol=1e-05, atol=1e-08, equal_nan=False), msg
 
-@step(u'embeddings are generated')
+
+@step('embeddings are generated')
 def step_assert_embeddings(context):
     assert context.n_prompts == len(context.embeddings), (f"unexpected response:\n"
                                                              f"context.n_prompts={context.n_prompts}\n"
@@ -482,17 +501,17 @@ def step_assert_embeddings(context):
         assert_embeddings(embedding)
 
 
-@step(u'an OAI compatible embeddings computation request for')
+@step('an OAI compatible embeddings computation request for')
 @async_run_until_complete
 async def step_oai_compute_embeddings(context):
     context.n_prompts = 1
-    context.embeddings = await request_oai_embeddings(context.text,
+    context.embeddings = await request_oai_embeddings(context_text(context),
                                                       base_url=context.base_url,
                                                       user_api_key=context.user_api_key,
                                                       model=context.model)
 
 
-@step(u'an OAI compatible embeddings computation request for multiple inputs')
+@step('an OAI compatible embeddings computation request for multiple inputs')
 @async_run_until_complete
 async def step_oai_compute_embeddings_multiple_inputs(context):
     context.embeddings = await request_oai_embeddings(context.prompts,
@@ -502,7 +521,7 @@ async def step_oai_compute_embeddings_multiple_inputs(context):
     context.prompts.clear()
 
 
-@step(u'concurrent embedding requests')
+@step('concurrent embedding requests')
 @async_run_until_complete()
 async def step_concurrent_embedding_requests(context):
     await concurrent_requests(context,
@@ -511,7 +530,7 @@ async def step_concurrent_embedding_requests(context):
                               base_url=context.base_url)
 
 
-@step(u'concurrent OAI embedding requests')
+@step('concurrent OAI embedding requests')
 @async_run_until_complete()
 async def step_concurrent_oai_embedding_requests(context):
     await concurrent_requests(context,
@@ -522,7 +541,7 @@ async def step_concurrent_oai_embedding_requests(context):
                               model=context.model)
 
 
-@step(u'all embeddings are generated')
+@step('all embeddings are generated')
 @async_run_until_complete()
 async def all_embeddings_are_generated(context):
     n_embedding_requests = await gather_tasks_results(context)
@@ -531,10 +550,10 @@ async def all_embeddings_are_generated(context):
         assert_embeddings(context.tasks_result.pop().pop())
 
 
-@step(u'tokenizing')
+@step('tokenizing')
 @async_run_until_complete
 async def step_tokenize(context):
-    context.tokenized_text = context.text
+    context.tokenized_text = context_text(context)
     async with aiohttp.ClientSession() as session:
         async with session.post(f'{context.base_url}/tokenize',
                                 json={
@@ -545,7 +564,7 @@ async def step_tokenize(context):
             context.tokens = tokenize_json['tokens']
 
 
-@step(u'tokens can be detokenize')
+@step('tokens can be detokenize')
 @async_run_until_complete
 async def step_detokenize(context):
     assert len(context.tokens) > 0
@@ -560,22 +579,23 @@ async def step_detokenize(context):
             assert context.tokenized_text == detokenize_json['content'].strip()
 
 
-@step(u'an OPTIONS request is sent from {origin}')
+@step('an OPTIONS request is sent from {origin}')
 @async_run_until_complete
 async def step_options_request(context, origin):
     async with aiohttp.ClientSession() as session:
+        headers = {'Authorization': f'Bearer {context.user_api_key}', 'Origin': origin}
         async with session.options(f'{context.base_url}/v1/chat/completions',
-                                   headers={"Origin": origin}) as response:
+                                    headers=headers) as response:
             assert response.status == 200
             context.options_response = response
 
 
-@step(u'CORS header {cors_header} is set to {cors_header_value}')
+@step('CORS header {cors_header} is set to {cors_header_value}')
 def step_check_options_header_value(context, cors_header, cors_header_value):
     assert context.options_response.headers[cors_header] == cors_header_value
 
 
-@step(u'prometheus metrics are exposed')
+@step('prometheus metrics are exposed')
 @async_run_until_complete
 async def step_prometheus_metrics_exported(context):
     async with aiohttp.ClientSession() as session:
@@ -597,14 +617,14 @@ async def step_prometheus_metrics_exported(context):
             assert metric_exported, "No metrics exported"
 
 
-@step(u'metric {metric_name} is {metric_value:d}')
+@step('metric {metric_name} is {metric_value:d}')
 def step_assert_metric_value(context, metric_name, metric_value):
     if metric_name not in context.metrics:
         assert False, f"no metric {metric_name} in {context.metrics.keys()}"
     assert context.metrics[metric_name].samples[0].value == metric_value, f"metric: {context.metrics[metric_name]}"
 
 
-@step(u'available models')
+@step('available models')
 def step_available_models(context):
     # openai client always expects an api_key
     openai.api_key = context.user_api_key if context.user_api_key is not None else 'nope'
@@ -612,14 +632,14 @@ def step_available_models(context):
     context.models = openai.Model.list().data
 
 
-@step(u'{n_model:d} models are supported')
+@step('{n_model:d} models are supported')
 def step_supported_models(context, n_model):
     if context.debug:
         print("server models available:", context.models)
     assert len(context.models) == n_model
 
 
-@step(u'model {i_model:d} is {param} {preposition} {param_value}')
+@step('model {i_model:d} is {param} {preposition} {param_value}')
 def step_supported_models(context, i_model, param, preposition, param_value):
     assert i_model < len(context.models)
     model = context.models[i_model]
@@ -722,7 +742,8 @@ async def oai_chat_completions(user_prompt,
     completion_response = {
         'content': '',
         'timings': {
-            'predicted_n': 0
+            'predicted_n': 0,
+            'prompt_n': 0
         }
     }
     if async_client:
@@ -763,7 +784,8 @@ async def oai_chat_completions(user_prompt,
                         completion_response = {
                             'content': chat_completion_raw['choices'][0]['message'],
                             'timings': {
-                                'predicted_n': chat_completion_raw['usage']['completion_tokens']
+                                'predicted_n': chat_completion_raw['usage']['completion_tokens'],
+                                'prompt_n': chat_completion_raw['usage']['prompt_tokens']
                             }
                         }
                     else:
@@ -779,7 +801,7 @@ async def oai_chat_completions(user_prompt,
                 stream=enable_streaming,
                 seed=seed
             )
-        except openai.error.APIError as e:
+        except openai.error.AuthenticationError as e:
             if expect_api_error is not None and expect_api_error:
                 return 401
             else:
@@ -792,13 +814,16 @@ async def oai_chat_completions(user_prompt,
                 if 'content' in delta:
                     completion_response['content'] += delta['content']
                     completion_response['timings']['predicted_n'] += 1
+                completion_response['truncated'] = chunk.choices[0].finish_reason != 'stop'
         else:
             assert len(chat_completion.choices) == 1
             completion_response = {
                 'content': chat_completion.choices[0].message.content,
                 'timings': {
-                    'predicted_n': chat_completion.usage.completion_tokens
-                }
+                    'predicted_n': chat_completion.usage.completion_tokens,
+                    'prompt_n': chat_completion.usage.prompt_tokens
+                    },
+                'truncated': chat_completion.choices[0].finish_reason != 'stop'
             }
     if debug:
         print("OAI response formatted to llama.cpp:", completion_response)
@@ -983,12 +1008,22 @@ async def completions_seed(context):
         else context.server_seed if hasattr(context, 'server_seed') else None
 
 
+def context_text(context):
+    return context.text.replace('\r', '')
+
+
 def start_server_background(context):
-    context.server_path = '../../../build/bin/server'
+    if os.name == 'nt':
+        context.server_path = '../../../build/bin/Release/server.exe'
+    else:
+        context.server_path = '../../../build/bin/server'
     if 'LLAMA_SERVER_BIN_PATH' in os.environ:
         context.server_path = os.environ['LLAMA_SERVER_BIN_PATH']
+    server_listen_addr = context.server_fqdn
+    if os.name == 'nt':
+        server_listen_addr = '0.0.0.0'
     server_args = [
-        '--host', context.server_fqdn,
+        '--host', server_listen_addr,
         '--port', context.server_port,
         '--model', context.model_file
     ]
@@ -1021,7 +1056,16 @@ def start_server_background(context):
     if 'SERVER_LOG_FORMAT_JSON' not in os.environ:
         server_args.extend(['--log-format', "text"])
     print(f"starting server with: {context.server_path} {server_args}\n")
+    flags = 0
+    if 'nt' == os.name:
+        flags |= subprocess.DETACHED_PROCESS
+        flags |= subprocess.CREATE_NEW_PROCESS_GROUP
+        flags |= subprocess.CREATE_NO_WINDOW
+
+    pkwargs = {
+        'creationflags': flags,
+    }
     context.server_process = subprocess.Popen(
         [str(arg) for arg in [context.server_path, *server_args]],
-        close_fds=True)
-    print(f"server pid={context.server_process.pid}")
+        **pkwargs)
+    print(f"server pid={context.server_process.pid}, behave pid={os.getpid()}")
diff --git a/examples/server/utils.hpp b/examples/server/utils.hpp
index df0a27782..48aeef4eb 100644
--- a/examples/server/utils.hpp
+++ b/examples/server/utils.hpp
@@ -14,6 +14,17 @@
 
 using json = nlohmann::json;
 
+// https://community.openai.com/t/openai-chat-list-of-error-codes-and-types/357791/11
+enum error_type {
+    ERROR_TYPE_INVALID_REQUEST,
+    ERROR_TYPE_AUTHENTICATION,
+    ERROR_TYPE_SERVER,
+    ERROR_TYPE_NOT_FOUND,
+    ERROR_TYPE_PERMISSION,
+    ERROR_TYPE_UNAVAILABLE, // custom error
+    ERROR_TYPE_NOT_SUPPORTED, // custom error
+};
+
 extern bool server_verbose;
 extern bool server_log_json;
 
@@ -378,7 +389,7 @@ static json oaicompat_completion_params_parse(
     return llama_params;
 }
 
-static json format_final_response_oaicompat(const json & request, json result, bool streaming = false) {
+static json format_final_response_oaicompat(const json & request, json result, const std::string & completion_id, bool streaming = false) {
     bool stopped_word        = result.count("stopped_word") != 0;
     bool stopped_eos         = json_value(result, "stopped_eos", false);
     int num_tokens_predicted = json_value(result, "tokens_predicted", 0);
@@ -412,7 +423,7 @@ static json format_final_response_oaicompat(const json & request, json result, b
             {"prompt_tokens",     num_prompt_tokens},
             {"total_tokens",      num_tokens_predicted + num_prompt_tokens}
         }},
-        {"id", gen_chatcmplid()}
+        {"id", completion_id}
     };
 
     if (server_verbose) {
@@ -427,7 +438,7 @@ static json format_final_response_oaicompat(const json & request, json result, b
 }
 
 // return value is vector as there is one case where we might need to generate two responses
-static std::vector<json> format_partial_response_oaicompat(json result) {
+static std::vector<json> format_partial_response_oaicompat(json result, const std::string & completion_id) {
     if (!result.contains("model") || !result.contains("oaicompat_token_ctr")) {
         return std::vector<json>({result});
     }
@@ -471,7 +482,7 @@ static std::vector<json> format_partial_response_oaicompat(json result) {
                                             {"role", "assistant"}
                                         }}}})},
                             {"created", t},
-                            {"id", gen_chatcmplid()},
+                            {"id", completion_id},
                             {"model", modelname},
                             {"object", "chat.completion.chunk"}};
 
@@ -482,7 +493,7 @@ static std::vector<json> format_partial_response_oaicompat(json result) {
                                                             {"content", content}}}
                                                             }})},
                             {"created", t},
-                            {"id", gen_chatcmplid()},
+                            {"id", completion_id},
                             {"model", modelname},
                             {"object", "chat.completion.chunk"}};
 
@@ -509,7 +520,7 @@ static std::vector<json> format_partial_response_oaicompat(json result) {
     json ret = json {
         {"choices", choices},
         {"created", t},
-        {"id",      gen_chatcmplid()},
+        {"id",      completion_id},
         {"model",   modelname},
         {"object",  "chat.completion.chunk"}
     };
@@ -542,3 +553,43 @@ static json format_detokenized_response(const std::string & content) {
         {"content", content}
     };
 }
+
+static json format_error_response(const std::string & message, const enum error_type type) {
+    std::string type_str;
+    int code = 500;
+    switch (type) {
+        case ERROR_TYPE_INVALID_REQUEST:
+            type_str = "invalid_request_error";
+            code = 400;
+            break;
+        case ERROR_TYPE_AUTHENTICATION:
+            type_str = "authentication_error";
+            code = 401;
+            break;
+        case ERROR_TYPE_NOT_FOUND:
+            type_str = "not_found_error";
+            code = 404;
+            break;
+        case ERROR_TYPE_SERVER:
+            type_str = "server_error";
+            code = 500;
+            break;
+        case ERROR_TYPE_PERMISSION:
+            type_str = "permission_error";
+            code = 403;
+            break;
+        case ERROR_TYPE_NOT_SUPPORTED:
+            type_str = "not_supported_error";
+            code = 501;
+            break;
+        case ERROR_TYPE_UNAVAILABLE:
+            type_str = "unavailable_error";
+            code = 503;
+            break;
+    }
+    return json {
+        {"code", code},
+        {"message", message},
+        {"type", type_str},
+    };
+}
diff --git a/ggml-common.h b/ggml-common.h
new file mode 100644
index 000000000..5dd918081
--- /dev/null
+++ b/ggml-common.h
@@ -0,0 +1,1424 @@
+#pragma once
+
+#if defined(GGML_COMMON_IMPL_C)
+#include <stdint.h>
+
+#define GGML_TABLE_BEGIN(type, name, size) static const type name[size] = {
+#define GGML_TABLE_END() };
+
+#define GGML_COMMON_IMPL
+#elif defined(GGML_COMMON_IMPL_METAL)
+#include <metal_stdlib>
+
+#define GGML_TABLE_BEGIN(type, name, size) static const constant type name[size] = {
+#define GGML_TABLE_END() };
+
+#define GGML_COMMON_IMPL
+#elif defined(GGML_COMMON_IMPL_CUDA)
+#include <cstdint>
+
+#define GGML_TABLE_BEGIN(type, name, size) static const __device__ type name[size] = {
+#define GGML_TABLE_END() };
+
+#define GGML_COMMON_IMPL
+#elif defined(GGML_COMMON_IMPL_SYCL)
+#include <cstdint>
+
+#define GGML_TABLE_BEGIN(type, name, size) static dpct::global_memory<const type, 1> name(sycl::range<1>(size), {
+#define GGML_TABLE_END() });
+
+#define GGML_COMMON_IMPL
+#endif
+
+#if defined(GGML_COMMON_IMPL)
+
+GGML_TABLE_BEGIN(uint8_t, kmask_iq2xs, 8)
+    1, 2, 4, 8, 16, 32, 64, 128
+GGML_TABLE_END()
+
+GGML_TABLE_BEGIN(uint8_t, ksigns_iq2xs, 128)
+      0, 129, 130,   3, 132,   5,   6, 135, 136,   9,  10, 139,  12, 141, 142,  15,
+    144,  17,  18, 147,  20, 149, 150,  23,  24, 153, 154,  27, 156,  29,  30, 159,
+    160,  33,  34, 163,  36, 165, 166,  39,  40, 169, 170,  43, 172,  45,  46, 175,
+     48, 177, 178,  51, 180,  53,  54, 183, 184,  57,  58, 187,  60, 189, 190,  63,
+    192,  65,  66, 195,  68, 197, 198,  71,  72, 201, 202,  75, 204,  77,  78, 207,
+     80, 209, 210,  83, 212,  85,  86, 215, 216,  89,  90, 219,  92, 221, 222,  95,
+     96, 225, 226,  99, 228, 101, 102, 231, 232, 105, 106, 235, 108, 237, 238, 111,
+    240, 113, 114, 243, 116, 245, 246, 119, 120, 249, 250, 123, 252, 125, 126, 255,
+GGML_TABLE_END()
+
+//#if __CUDA_ARCH__ >= MIN_CC_DP4A // lowest compute capability for integer intrinsics
+GGML_TABLE_BEGIN(uint64_t, ksigns64, 128)
+    0x0000000000000000, 0xff000000000000ff, 0xff0000000000ff00, 0x000000000000ffff,
+    0xff00000000ff0000, 0x0000000000ff00ff, 0x0000000000ffff00, 0xff00000000ffffff,
+    0xff000000ff000000, 0x00000000ff0000ff, 0x00000000ff00ff00, 0xff000000ff00ffff,
+    0x00000000ffff0000, 0xff000000ffff00ff, 0xff000000ffffff00, 0x00000000ffffffff,
+    0xff0000ff00000000, 0x000000ff000000ff, 0x000000ff0000ff00, 0xff0000ff0000ffff,
+    0x000000ff00ff0000, 0xff0000ff00ff00ff, 0xff0000ff00ffff00, 0x000000ff00ffffff,
+    0x000000ffff000000, 0xff0000ffff0000ff, 0xff0000ffff00ff00, 0x000000ffff00ffff,
+    0xff0000ffffff0000, 0x000000ffffff00ff, 0x000000ffffffff00, 0xff0000ffffffffff,
+    0xff00ff0000000000, 0x0000ff00000000ff, 0x0000ff000000ff00, 0xff00ff000000ffff,
+    0x0000ff0000ff0000, 0xff00ff0000ff00ff, 0xff00ff0000ffff00, 0x0000ff0000ffffff,
+    0x0000ff00ff000000, 0xff00ff00ff0000ff, 0xff00ff00ff00ff00, 0x0000ff00ff00ffff,
+    0xff00ff00ffff0000, 0x0000ff00ffff00ff, 0x0000ff00ffffff00, 0xff00ff00ffffffff,
+    0x0000ffff00000000, 0xff00ffff000000ff, 0xff00ffff0000ff00, 0x0000ffff0000ffff,
+    0xff00ffff00ff0000, 0x0000ffff00ff00ff, 0x0000ffff00ffff00, 0xff00ffff00ffffff,
+    0xff00ffffff000000, 0x0000ffffff0000ff, 0x0000ffffff00ff00, 0xff00ffffff00ffff,
+    0x0000ffffffff0000, 0xff00ffffffff00ff, 0xff00ffffffffff00, 0x0000ffffffffffff,
+    0xffff000000000000, 0x00ff0000000000ff, 0x00ff00000000ff00, 0xffff00000000ffff,
+    0x00ff000000ff0000, 0xffff000000ff00ff, 0xffff000000ffff00, 0x00ff000000ffffff,
+    0x00ff0000ff000000, 0xffff0000ff0000ff, 0xffff0000ff00ff00, 0x00ff0000ff00ffff,
+    0xffff0000ffff0000, 0x00ff0000ffff00ff, 0x00ff0000ffffff00, 0xffff0000ffffffff,
+    0x00ff00ff00000000, 0xffff00ff000000ff, 0xffff00ff0000ff00, 0x00ff00ff0000ffff,
+    0xffff00ff00ff0000, 0x00ff00ff00ff00ff, 0x00ff00ff00ffff00, 0xffff00ff00ffffff,
+    0xffff00ffff000000, 0x00ff00ffff0000ff, 0x00ff00ffff00ff00, 0xffff00ffff00ffff,
+    0x00ff00ffffff0000, 0xffff00ffffff00ff, 0xffff00ffffffff00, 0x00ff00ffffffffff,
+    0x00ffff0000000000, 0xffffff00000000ff, 0xffffff000000ff00, 0x00ffff000000ffff,
+    0xffffff0000ff0000, 0x00ffff0000ff00ff, 0x00ffff0000ffff00, 0xffffff0000ffffff,
+    0xffffff00ff000000, 0x00ffff00ff0000ff, 0x00ffff00ff00ff00, 0xffffff00ff00ffff,
+    0x00ffff00ffff0000, 0xffffff00ffff00ff, 0xffffff00ffffff00, 0x00ffff00ffffffff,
+    0xffffffff00000000, 0x00ffffff000000ff, 0x00ffffff0000ff00, 0xffffffff0000ffff,
+    0x00ffffff00ff0000, 0xffffffff00ff00ff, 0xffffffff00ffff00, 0x00ffffff00ffffff,
+    0x00ffffffff000000, 0xffffffffff0000ff, 0xffffffffff00ff00, 0x00ffffffff00ffff,
+    0xffffffffffff0000, 0x00ffffffffff00ff, 0x00ffffffffffff00, 0xffffffffffffffff,
+GGML_TABLE_END()
+//#endif
+
+
+GGML_TABLE_BEGIN(uint64_t, iq2xxs_grid, 256)
+    0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08,
+    0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x08080808082b0808,
+    0x08080808082b082b, 0x08080808082b2b08, 0x08080808082b2b2b, 0x0808080819080819,
+    0x0808080819081908, 0x0808080819190808, 0x0808080819192b08, 0x08080808192b0819,
+    0x08080808192b1908, 0x080808082b080808, 0x080808082b08082b, 0x080808082b082b2b,
+    0x080808082b2b082b, 0x0808081908080819, 0x0808081908081908, 0x0808081908190808,
+    0x0808081908191919, 0x0808081919080808, 0x080808192b081908, 0x080808192b192b08,
+    0x0808082b08080808, 0x0808082b0808082b, 0x0808082b082b082b, 0x0808082b2b08082b,
+    0x0808190808080819, 0x0808190808081908, 0x0808190808190808, 0x08081908082b0819,
+    0x08081908082b1908, 0x0808190819080808, 0x080819081908082b, 0x0808190819082b08,
+    0x08081908192b0808, 0x080819082b080819, 0x080819082b081908, 0x080819082b190808,
+    0x080819082b2b1908, 0x0808191908080808, 0x080819190808082b, 0x0808191908082b08,
+    0x08081919082b0808, 0x080819191908192b, 0x08081919192b2b19, 0x080819192b080808,
+    0x080819192b190819, 0x0808192b08082b19, 0x0808192b08190808, 0x0808192b19080808,
+    0x0808192b2b081908, 0x0808192b2b2b1908, 0x08082b0808080808, 0x08082b0808081919,
+    0x08082b0808082b08, 0x08082b0808191908, 0x08082b08082b2b08, 0x08082b0819080819,
+    0x08082b0819081908, 0x08082b0819190808, 0x08082b081919082b, 0x08082b082b082b08,
+    0x08082b1908081908, 0x08082b1919080808, 0x08082b2b0808082b, 0x08082b2b08191908,
+    0x0819080808080819, 0x0819080808081908, 0x0819080808190808, 0x08190808082b0819,
+    0x0819080819080808, 0x08190808192b0808, 0x081908082b081908, 0x081908082b190808,
+    0x081908082b191919, 0x0819081908080808, 0x0819081908082b08, 0x08190819082b0808,
+    0x0819081919190808, 0x0819081919192b2b, 0x081908192b080808, 0x0819082b082b1908,
+    0x0819082b19081919, 0x0819190808080808, 0x0819190808082b08, 0x08191908082b0808,
+    0x08191908082b1919, 0x0819190819082b19, 0x081919082b080808, 0x0819191908192b08,
+    0x08191919192b082b, 0x0819192b08080808, 0x0819192b0819192b, 0x08192b0808080819,
+    0x08192b0808081908, 0x08192b0808190808, 0x08192b0819080808, 0x08192b082b080819,
+    0x08192b1908080808, 0x08192b1908081919, 0x08192b192b2b0808, 0x08192b2b19190819,
+    0x082b080808080808, 0x082b08080808082b, 0x082b080808082b2b, 0x082b080819081908,
+    0x082b0808192b0819, 0x082b08082b080808, 0x082b08082b08082b, 0x082b0819082b2b19,
+    0x082b081919082b08, 0x082b082b08080808, 0x082b082b0808082b, 0x082b190808080819,
+    0x082b190808081908, 0x082b190808190808, 0x082b190819080808, 0x082b19081919192b,
+    0x082b191908080808, 0x082b191919080819, 0x082b1919192b1908, 0x082b192b2b190808,
+    0x082b2b0808082b08, 0x082b2b08082b0808, 0x082b2b082b191908, 0x082b2b2b19081908,
+    0x1908080808080819, 0x1908080808081908, 0x1908080808190808, 0x1908080808192b08,
+    0x19080808082b0819, 0x19080808082b1908, 0x1908080819080808, 0x1908080819082b08,
+    0x190808081919192b, 0x19080808192b0808, 0x190808082b080819, 0x190808082b081908,
+    0x190808082b190808, 0x1908081908080808, 0x19080819082b0808, 0x19080819192b0819,
+    0x190808192b080808, 0x190808192b081919, 0x1908082b08080819, 0x1908082b08190808,
+    0x1908082b19082b08, 0x1908082b1919192b, 0x1908082b192b2b08, 0x1908190808080808,
+    0x1908190808082b08, 0x19081908082b0808, 0x190819082b080808, 0x190819082b192b19,
+    0x190819190819082b, 0x19081919082b1908, 0x1908192b08080808, 0x19082b0808080819,
+    0x19082b0808081908, 0x19082b0808190808, 0x19082b0819080808, 0x19082b0819081919,
+    0x19082b1908080808, 0x19082b1919192b08, 0x19082b19192b0819, 0x19082b192b08082b,
+    0x19082b2b19081919, 0x19082b2b2b190808, 0x1919080808080808, 0x1919080808082b08,
+    0x1919080808190819, 0x1919080808192b19, 0x19190808082b0808, 0x191908082b080808,
+    0x191908082b082b08, 0x1919081908081908, 0x191908191908082b, 0x191908192b2b1908,
+    0x1919082b2b190819, 0x191919082b190808, 0x191919082b19082b, 0x1919191908082b2b,
+    0x1919192b08080819, 0x1919192b19191908, 0x19192b0808080808, 0x19192b0808190819,
+    0x19192b0808192b19, 0x19192b08192b1908, 0x19192b1919080808, 0x19192b2b08082b08,
+    0x192b080808081908, 0x192b080808190808, 0x192b080819080808, 0x192b0808192b2b08,
+    0x192b081908080808, 0x192b081919191919, 0x192b082b08192b08, 0x192b082b192b0808,
+    0x192b190808080808, 0x192b190808081919, 0x192b191908190808, 0x192b19190819082b,
+    0x192b19192b081908, 0x192b2b081908082b, 0x2b08080808080808, 0x2b0808080808082b,
+    0x2b08080808082b2b, 0x2b08080819080819, 0x2b0808082b08082b, 0x2b08081908081908,
+    0x2b08081908192b08, 0x2b08081919080808, 0x2b08082b08190819, 0x2b08190808080819,
+    0x2b08190808081908, 0x2b08190808190808, 0x2b08190808191919, 0x2b08190819080808,
+    0x2b081908192b0808, 0x2b08191908080808, 0x2b0819191908192b, 0x2b0819192b191908,
+    0x2b08192b08082b19, 0x2b08192b19080808, 0x2b08192b192b0808, 0x2b082b080808082b,
+    0x2b082b1908081908, 0x2b082b2b08190819, 0x2b19080808081908, 0x2b19080808190808,
+    0x2b190808082b1908, 0x2b19080819080808, 0x2b1908082b2b0819, 0x2b1908190819192b,
+    0x2b1908192b080808, 0x2b19082b19081919, 0x2b19190808080808, 0x2b191908082b082b,
+    0x2b19190819081908, 0x2b19191919190819, 0x2b192b082b080819, 0x2b192b19082b0808,
+    0x2b2b08080808082b, 0x2b2b080819190808, 0x2b2b08082b081919, 0x2b2b081908082b19,
+    0x2b2b082b08080808, 0x2b2b190808192b08, 0x2b2b2b0819190808, 0x2b2b2b1908081908,
+GGML_TABLE_END()
+
+GGML_TABLE_BEGIN(uint64_t, iq2xs_grid, 512)
+    0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08,
+    0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x080808080819192b,
+    0x0808080808192b19, 0x08080808082b0808, 0x08080808082b082b, 0x08080808082b1919,
+    0x08080808082b2b08, 0x0808080819080819, 0x0808080819081908, 0x080808081908192b,
+    0x0808080819082b19, 0x0808080819190808, 0x080808081919082b, 0x0808080819191919,
+    0x0808080819192b08, 0x08080808192b0819, 0x08080808192b1908, 0x080808082b080808,
+    0x080808082b08082b, 0x080808082b081919, 0x080808082b082b08, 0x080808082b190819,
+    0x080808082b191908, 0x080808082b192b19, 0x080808082b2b0808, 0x0808081908080819,
+    0x0808081908081908, 0x080808190808192b, 0x0808081908082b19, 0x0808081908190808,
+    0x080808190819082b, 0x0808081908191919, 0x0808081908192b08, 0x0808081908192b2b,
+    0x08080819082b0819, 0x08080819082b1908, 0x0808081919080808, 0x080808191908082b,
+    0x0808081919081919, 0x0808081919082b08, 0x0808081919190819, 0x0808081919191908,
+    0x08080819192b0808, 0x08080819192b2b08, 0x080808192b080819, 0x080808192b081908,
+    0x080808192b190808, 0x0808082b08080808, 0x0808082b0808082b, 0x0808082b08081919,
+    0x0808082b08082b08, 0x0808082b08190819, 0x0808082b08191908, 0x0808082b082b0808,
+    0x0808082b19080819, 0x0808082b19081908, 0x0808082b19190808, 0x0808082b19191919,
+    0x0808082b2b080808, 0x0808082b2b082b2b, 0x0808190808080819, 0x0808190808081908,
+    0x080819080808192b, 0x0808190808082b19, 0x0808190808190808, 0x080819080819082b,
+    0x0808190808191919, 0x0808190808192b08, 0x08081908082b0819, 0x08081908082b1908,
+    0x0808190819080808, 0x080819081908082b, 0x0808190819081919, 0x0808190819082b08,
+    0x0808190819190819, 0x0808190819191908, 0x080819081919192b, 0x08081908192b0808,
+    0x080819082b080819, 0x080819082b081908, 0x080819082b190808, 0x0808191908080808,
+    0x080819190808082b, 0x0808191908081919, 0x0808191908082b08, 0x0808191908190819,
+    0x0808191908191908, 0x08081919082b0808, 0x0808191919080819, 0x0808191919081908,
+    0x0808191919190808, 0x08081919192b0819, 0x080819192b080808, 0x0808192b08080819,
+    0x0808192b08081908, 0x0808192b08190808, 0x0808192b082b192b, 0x0808192b19080808,
+    0x0808192b1908082b, 0x0808192b2b081908, 0x08082b0808080808, 0x08082b080808082b,
+    0x08082b0808081919, 0x08082b0808082b08, 0x08082b0808082b2b, 0x08082b0808190819,
+    0x08082b0808191908, 0x08082b08082b0808, 0x08082b08082b1919, 0x08082b0819080819,
+    0x08082b0819081908, 0x08082b0819190808, 0x08082b0819192b08, 0x08082b082b080808,
+    0x08082b082b2b0808, 0x08082b082b2b2b2b, 0x08082b1908080819, 0x08082b1908081908,
+    0x08082b1908190808, 0x08082b1919080808, 0x08082b192b080819, 0x08082b192b082b19,
+    0x08082b2b08080808, 0x08082b2b082b0808, 0x08082b2b082b2b08, 0x08082b2b2b19192b,
+    0x08082b2b2b2b0808, 0x0819080808080819, 0x0819080808081908, 0x081908080808192b,
+    0x0819080808082b19, 0x0819080808190808, 0x081908080819082b, 0x0819080808191919,
+    0x0819080808192b08, 0x08190808082b0819, 0x08190808082b1908, 0x0819080819080808,
+    0x081908081908082b, 0x0819080819081919, 0x0819080819082b08, 0x0819080819190819,
+    0x0819080819191908, 0x08190808192b0808, 0x08190808192b2b2b, 0x081908082b080819,
+    0x081908082b081908, 0x081908082b190808, 0x0819081908080808, 0x081908190808082b,
+    0x0819081908081919, 0x0819081908082b08, 0x0819081908190819, 0x0819081908191908,
+    0x08190819082b0808, 0x0819081919080819, 0x0819081919081908, 0x0819081919190808,
+    0x081908192b080808, 0x081908192b191908, 0x081908192b19192b, 0x0819082b08080819,
+    0x0819082b08081908, 0x0819082b0808192b, 0x0819082b08190808, 0x0819082b19080808,
+    0x0819082b192b0808, 0x0819190808080808, 0x081919080808082b, 0x0819190808081919,
+    0x0819190808082b08, 0x0819190808190819, 0x0819190808191908, 0x08191908082b0808,
+    0x0819190819080819, 0x0819190819081908, 0x0819190819082b19, 0x0819190819190808,
+    0x08191908192b1908, 0x081919082b080808, 0x0819191908080819, 0x0819191908081908,
+    0x0819191908190808, 0x0819191919080808, 0x0819192b08080808, 0x0819192b08191908,
+    0x0819192b19082b19, 0x08192b0808080819, 0x08192b0808081908, 0x08192b0808190808,
+    0x08192b080819082b, 0x08192b0819080808, 0x08192b0819191908, 0x08192b082b08192b,
+    0x08192b1908080808, 0x08192b1908081919, 0x08192b19192b192b, 0x08192b2b19190819,
+    0x08192b2b2b2b2b19, 0x082b080808080808, 0x082b08080808082b, 0x082b080808081919,
+    0x082b080808082b08, 0x082b080808082b2b, 0x082b080808190819, 0x082b080808191908,
+    0x082b0808082b0808, 0x082b080819080819, 0x082b080819081908, 0x082b080819190808,
+    0x082b08082b080808, 0x082b08082b2b0808, 0x082b081908080819, 0x082b081908081908,
+    0x082b081908190808, 0x082b081919080808, 0x082b081919082b08, 0x082b0819192b1919,
+    0x082b082b08080808, 0x082b082b082b082b, 0x082b082b2b080808, 0x082b082b2b2b2b08,
+    0x082b190808080819, 0x082b190808081908, 0x082b190808190808, 0x082b1908082b2b19,
+    0x082b190819080808, 0x082b191908080808, 0x082b191919080819, 0x082b19191919082b,
+    0x082b19192b192b19, 0x082b192b08080819, 0x082b192b08192b2b, 0x082b192b2b2b192b,
+    0x082b2b0808080808, 0x082b2b0808082b08, 0x082b2b0808082b2b, 0x082b2b08082b0808,
+    0x082b2b0819191919, 0x082b2b082b082b08, 0x082b2b082b2b082b, 0x082b2b19192b2b08,
+    0x082b2b192b190808, 0x082b2b2b08082b08, 0x082b2b2b082b0808, 0x082b2b2b2b08082b,
+    0x082b2b2b2b082b08, 0x082b2b2b2b082b2b, 0x1908080808080819, 0x1908080808081908,
+    0x190808080808192b, 0x1908080808082b19, 0x1908080808190808, 0x190808080819082b,
+    0x1908080808191919, 0x1908080808192b08, 0x19080808082b0819, 0x19080808082b1908,
+    0x1908080819080808, 0x190808081908082b, 0x1908080819081919, 0x1908080819082b08,
+    0x1908080819082b2b, 0x1908080819190819, 0x1908080819191908, 0x19080808192b0808,
+    0x19080808192b1919, 0x190808082b080819, 0x190808082b081908, 0x190808082b190808,
+    0x1908081908080808, 0x190808190808082b, 0x1908081908081919, 0x1908081908082b08,
+    0x1908081908190819, 0x1908081908191908, 0x19080819082b0808, 0x1908081919080819,
+    0x1908081919081908, 0x1908081919190808, 0x190808192b080808, 0x190808192b081919,
+    0x190808192b2b082b, 0x1908082b08080819, 0x1908082b08081908, 0x1908082b08190808,
+    0x1908082b0819082b, 0x1908082b082b2b19, 0x1908082b19080808, 0x1908190808080808,
+    0x190819080808082b, 0x1908190808081919, 0x1908190808082b08, 0x1908190808190819,
+    0x1908190808191908, 0x1908190808192b19, 0x19081908082b0808, 0x1908190819080819,
+    0x1908190819081908, 0x1908190819190808, 0x190819082b080808, 0x190819082b191908,
+    0x1908191908080819, 0x1908191908081908, 0x1908191908190808, 0x19081919082b1908,
+    0x1908191919080808, 0x190819192b192b2b, 0x1908192b08080808, 0x1908192b08082b2b,
+    0x1908192b19081908, 0x1908192b19190808, 0x19082b0808080819, 0x19082b0808081908,
+    0x19082b0808190808, 0x19082b0819080808, 0x19082b0819081919, 0x19082b0819191908,
+    0x19082b08192b082b, 0x19082b1908080808, 0x19082b1908190819, 0x19082b1919081908,
+    0x19082b1919190808, 0x19082b19192b2b19, 0x19082b2b08081908, 0x1919080808080808,
+    0x191908080808082b, 0x1919080808081919, 0x1919080808082b08, 0x1919080808190819,
+    0x1919080808191908, 0x19190808082b0808, 0x19190808082b2b08, 0x1919080819080819,
+    0x1919080819081908, 0x1919080819190808, 0x191908082b080808, 0x1919081908080819,
+    0x1919081908081908, 0x1919081908190808, 0x1919081908191919, 0x1919081919080808,
+    0x191908191908082b, 0x1919082b08080808, 0x1919082b19081908, 0x1919082b2b2b2b2b,
+    0x1919190808080819, 0x1919190808081908, 0x1919190808190808, 0x19191908082b0819,
+    0x1919190819080808, 0x19191908192b0808, 0x191919082b080819, 0x191919082b2b0819,
+    0x1919191908080808, 0x1919191908082b08, 0x191919192b080808, 0x191919192b082b08,
+    0x1919192b082b0819, 0x1919192b192b2b08, 0x1919192b2b2b0819, 0x19192b0808080808,
+    0x19192b0808191908, 0x19192b0819080819, 0x19192b0819190808, 0x19192b082b192b19,
+    0x19192b1908192b2b, 0x19192b1919080808, 0x19192b191908082b, 0x19192b2b2b081919,
+    0x192b080808080819, 0x192b080808081908, 0x192b080808190808, 0x192b080819080808,
+    0x192b080819191908, 0x192b0808192b082b, 0x192b08082b08192b, 0x192b08082b2b2b19,
+    0x192b081908080808, 0x192b082b082b1908, 0x192b082b19082b2b, 0x192b082b2b19082b,
+    0x192b190808080808, 0x192b19080819192b, 0x192b191908190808, 0x192b191919080808,
+    0x192b191919081919, 0x192b19192b2b1908, 0x192b2b0808080819, 0x192b2b08192b2b2b,
+    0x192b2b19082b1919, 0x192b2b2b0808192b, 0x192b2b2b19191908, 0x192b2b2b192b082b,
+    0x2b08080808080808, 0x2b0808080808082b, 0x2b08080808081919, 0x2b08080808082b08,
+    0x2b08080808190819, 0x2b08080808191908, 0x2b080808082b0808, 0x2b080808082b2b2b,
+    0x2b08080819080819, 0x2b08080819081908, 0x2b08080819190808, 0x2b0808082b080808,
+    0x2b0808082b08082b, 0x2b0808082b2b2b08, 0x2b0808082b2b2b2b, 0x2b08081908080819,
+    0x2b08081908081908, 0x2b0808190808192b, 0x2b08081908190808, 0x2b08081919080808,
+    0x2b08081919190819, 0x2b08081919192b19, 0x2b08082b08080808, 0x2b08082b082b0808,
+    0x2b08082b2b080808, 0x2b08082b2b08082b, 0x2b08082b2b2b0808, 0x2b08082b2b2b2b08,
+    0x2b08190808080819, 0x2b08190808081908, 0x2b08190808190808, 0x2b0819080819082b,
+    0x2b08190808191919, 0x2b08190819080808, 0x2b081908192b0808, 0x2b0819082b082b19,
+    0x2b08191908080808, 0x2b08191919081908, 0x2b0819192b2b1919, 0x2b08192b08192b08,
+    0x2b08192b192b2b2b, 0x2b082b0808080808, 0x2b082b0808082b08, 0x2b082b08082b1919,
+    0x2b082b0819192b2b, 0x2b082b082b080808, 0x2b082b082b08082b, 0x2b082b082b2b2b08,
+    0x2b082b190808192b, 0x2b082b2b082b082b, 0x2b082b2b2b080808, 0x2b082b2b2b082b08,
+    0x2b082b2b2b19192b, 0x2b082b2b2b2b2b08, 0x2b19080808080819, 0x2b19080808081908,
+    0x2b19080808190808, 0x2b19080819080808, 0x2b1908081919192b, 0x2b1908082b081908,
+    0x2b19081908080808, 0x2b190819082b082b, 0x2b190819192b1908, 0x2b19082b1919192b,
+    0x2b19082b2b082b19, 0x2b19190808080808, 0x2b19190808081919, 0x2b19190819081908,
+    0x2b19190819190808, 0x2b19190819192b08, 0x2b191919082b2b19, 0x2b1919192b190808,
+    0x2b1919192b19082b, 0x2b19192b19080819, 0x2b192b0819190819, 0x2b192b082b2b192b,
+    0x2b192b1919082b19, 0x2b192b2b08191919, 0x2b192b2b192b0808, 0x2b2b080808080808,
+    0x2b2b08080808082b, 0x2b2b080808082b08, 0x2b2b080808082b2b, 0x2b2b0808082b0808,
+    0x2b2b0808082b2b2b, 0x2b2b08082b2b0808, 0x2b2b081919190819, 0x2b2b081919192b19,
+    0x2b2b08192b2b192b, 0x2b2b082b08080808, 0x2b2b082b0808082b, 0x2b2b082b08082b08,
+    0x2b2b082b082b2b2b, 0x2b2b082b2b080808, 0x2b2b082b2b2b0808, 0x2b2b190819080808,
+    0x2b2b19082b191919, 0x2b2b192b192b1919, 0x2b2b192b2b192b08, 0x2b2b2b0808082b2b,
+    0x2b2b2b08082b0808, 0x2b2b2b08082b082b, 0x2b2b2b08082b2b08, 0x2b2b2b082b2b0808,
+    0x2b2b2b082b2b2b08, 0x2b2b2b1908081908, 0x2b2b2b192b081908, 0x2b2b2b192b08192b,
+    0x2b2b2b2b082b2b08, 0x2b2b2b2b082b2b2b, 0x2b2b2b2b2b190819, 0x2b2b2b2b2b2b2b2b,
+GGML_TABLE_END()
+
+GGML_TABLE_BEGIN(uint64_t, iq2s_grid, 1024)
+    0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08,
+    0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x080808080819192b,
+    0x0808080808192b19, 0x08080808082b0808, 0x08080808082b082b, 0x08080808082b1919,
+    0x08080808082b2b08, 0x0808080819080819, 0x0808080819081908, 0x080808081908192b,
+    0x0808080819082b19, 0x0808080819190808, 0x080808081919082b, 0x0808080819191919,
+    0x0808080819192b08, 0x08080808192b0819, 0x08080808192b1908, 0x08080808192b192b,
+    0x08080808192b2b19, 0x080808082b080808, 0x080808082b08082b, 0x080808082b081919,
+    0x080808082b082b08, 0x080808082b190819, 0x080808082b191908, 0x080808082b2b0808,
+    0x080808082b2b1919, 0x080808082b2b2b2b, 0x0808081908080819, 0x0808081908081908,
+    0x080808190808192b, 0x0808081908082b19, 0x0808081908190808, 0x080808190819082b,
+    0x0808081908191919, 0x0808081908192b08, 0x08080819082b0819, 0x08080819082b1908,
+    0x0808081919080808, 0x080808191908082b, 0x0808081919081919, 0x0808081919082b08,
+    0x0808081919190819, 0x0808081919191908, 0x080808191919192b, 0x0808081919192b19,
+    0x08080819192b0808, 0x08080819192b1919, 0x08080819192b2b08, 0x080808192b080819,
+    0x080808192b081908, 0x080808192b190808, 0x080808192b19082b, 0x080808192b191919,
+    0x080808192b2b0819, 0x080808192b2b1908, 0x0808082b08080808, 0x0808082b0808082b,
+    0x0808082b08081919, 0x0808082b08082b08, 0x0808082b08190819, 0x0808082b08191908,
+    0x0808082b082b0808, 0x0808082b082b2b2b, 0x0808082b19080819, 0x0808082b19081908,
+    0x0808082b1908192b, 0x0808082b19082b19, 0x0808082b19190808, 0x0808082b19191919,
+    0x0808082b2b080808, 0x0808082b2b081919, 0x0808082b2b082b2b, 0x0808082b2b191908,
+    0x0808082b2b2b082b, 0x0808190808080819, 0x0808190808081908, 0x080819080808192b,
+    0x0808190808082b19, 0x0808190808190808, 0x080819080819082b, 0x0808190808191919,
+    0x0808190808192b08, 0x08081908082b0819, 0x08081908082b1908, 0x08081908082b192b,
+    0x08081908082b2b19, 0x0808190819080808, 0x080819081908082b, 0x0808190819081919,
+    0x0808190819082b08, 0x0808190819082b2b, 0x0808190819190819, 0x0808190819191908,
+    0x080819081919192b, 0x0808190819192b19, 0x08081908192b0808, 0x08081908192b082b,
+    0x08081908192b1919, 0x080819082b080819, 0x080819082b081908, 0x080819082b08192b,
+    0x080819082b082b19, 0x080819082b190808, 0x080819082b191919, 0x080819082b192b08,
+    0x080819082b2b0819, 0x080819082b2b1908, 0x0808191908080808, 0x080819190808082b,
+    0x0808191908081919, 0x0808191908082b08, 0x0808191908082b2b, 0x0808191908190819,
+    0x0808191908191908, 0x080819190819192b, 0x0808191908192b19, 0x08081919082b0808,
+    0x08081919082b1919, 0x08081919082b2b08, 0x0808191919080819, 0x0808191919081908,
+    0x080819191908192b, 0x0808191919082b19, 0x0808191919190808, 0x080819191919082b,
+    0x0808191919191919, 0x0808191919192b08, 0x08081919192b0819, 0x08081919192b1908,
+    0x080819192b080808, 0x080819192b08082b, 0x080819192b081919, 0x080819192b082b08,
+    0x080819192b190819, 0x080819192b191908, 0x080819192b2b0808, 0x0808192b08080819,
+    0x0808192b08081908, 0x0808192b0808192b, 0x0808192b08082b19, 0x0808192b08190808,
+    0x0808192b08191919, 0x0808192b19080808, 0x0808192b19081919, 0x0808192b19082b08,
+    0x0808192b19190819, 0x0808192b19191908, 0x0808192b192b0808, 0x0808192b2b080819,
+    0x0808192b2b081908, 0x0808192b2b190808, 0x08082b0808080808, 0x08082b080808082b,
+    0x08082b0808081919, 0x08082b0808082b08, 0x08082b0808190819, 0x08082b0808191908,
+    0x08082b080819192b, 0x08082b0808192b19, 0x08082b08082b0808, 0x08082b08082b1919,
+    0x08082b08082b2b2b, 0x08082b0819080819, 0x08082b0819081908, 0x08082b081908192b,
+    0x08082b0819082b19, 0x08082b0819190808, 0x08082b081919082b, 0x08082b0819191919,
+    0x08082b0819192b08, 0x08082b08192b0819, 0x08082b08192b1908, 0x08082b082b080808,
+    0x08082b082b081919, 0x08082b082b191908, 0x08082b082b2b2b2b, 0x08082b1908080819,
+    0x08082b1908081908, 0x08082b1908190808, 0x08082b190819082b, 0x08082b1908191919,
+    0x08082b1908192b08, 0x08082b19082b0819, 0x08082b1919080808, 0x08082b1919081919,
+    0x08082b1919082b08, 0x08082b1919190819, 0x08082b1919191908, 0x08082b19192b0808,
+    0x08082b192b080819, 0x08082b192b190808, 0x08082b2b08080808, 0x08082b2b08190819,
+    0x08082b2b08191908, 0x08082b2b082b082b, 0x08082b2b082b2b08, 0x08082b2b082b2b2b,
+    0x08082b2b19190808, 0x08082b2b2b192b19, 0x0819080808080819, 0x0819080808081908,
+    0x081908080808192b, 0x0819080808082b19, 0x0819080808190808, 0x081908080819082b,
+    0x0819080808191919, 0x0819080808192b08, 0x08190808082b0819, 0x08190808082b1908,
+    0x08190808082b192b, 0x0819080819080808, 0x081908081908082b, 0x0819080819081919,
+    0x0819080819082b08, 0x0819080819190819, 0x0819080819191908, 0x081908081919192b,
+    0x0819080819192b19, 0x08190808192b0808, 0x08190808192b082b, 0x08190808192b1919,
+    0x08190808192b2b08, 0x081908082b080819, 0x081908082b081908, 0x081908082b08192b,
+    0x081908082b190808, 0x081908082b191919, 0x081908082b192b08, 0x081908082b2b0819,
+    0x081908082b2b1908, 0x0819081908080808, 0x081908190808082b, 0x0819081908081919,
+    0x0819081908082b08, 0x0819081908082b2b, 0x0819081908190819, 0x0819081908191908,
+    0x081908190819192b, 0x0819081908192b19, 0x08190819082b0808, 0x08190819082b082b,
+    0x08190819082b1919, 0x08190819082b2b08, 0x0819081919080819, 0x0819081919081908,
+    0x081908191908192b, 0x0819081919082b19, 0x0819081919190808, 0x081908191919082b,
+    0x0819081919191919, 0x0819081919192b08, 0x08190819192b0819, 0x08190819192b1908,
+    0x081908192b080808, 0x081908192b08082b, 0x081908192b081919, 0x081908192b082b08,
+    0x081908192b190819, 0x081908192b191908, 0x0819082b08080819, 0x0819082b08081908,
+    0x0819082b08082b19, 0x0819082b08190808, 0x0819082b08191919, 0x0819082b082b0819,
+    0x0819082b082b1908, 0x0819082b19080808, 0x0819082b19081919, 0x0819082b19190819,
+    0x0819082b19191908, 0x0819082b2b080819, 0x0819082b2b081908, 0x0819082b2b190808,
+    0x0819190808080808, 0x081919080808082b, 0x0819190808081919, 0x0819190808082b08,
+    0x0819190808190819, 0x0819190808191908, 0x081919080819192b, 0x0819190808192b19,
+    0x08191908082b0808, 0x08191908082b1919, 0x08191908082b2b08, 0x0819190819080819,
+    0x0819190819081908, 0x081919081908192b, 0x0819190819082b19, 0x0819190819190808,
+    0x081919081919082b, 0x0819190819191919, 0x0819190819192b08, 0x08191908192b0819,
+    0x08191908192b1908, 0x081919082b080808, 0x081919082b08082b, 0x081919082b081919,
+    0x081919082b082b08, 0x081919082b190819, 0x081919082b191908, 0x081919082b2b0808,
+    0x0819191908080819, 0x0819191908081908, 0x081919190808192b, 0x0819191908082b19,
+    0x0819191908190808, 0x081919190819082b, 0x0819191908191919, 0x0819191908192b08,
+    0x08191919082b0819, 0x08191919082b1908, 0x0819191919080808, 0x081919191908082b,
+    0x0819191919081919, 0x0819191919082b08, 0x0819191919190819, 0x0819191919191908,
+    0x08191919192b0808, 0x081919192b080819, 0x081919192b081908, 0x081919192b190808,
+    0x0819192b08080808, 0x0819192b08081919, 0x0819192b08082b08, 0x0819192b08190819,
+    0x0819192b08191908, 0x0819192b082b0808, 0x0819192b19080819, 0x0819192b19081908,
+    0x0819192b19190808, 0x0819192b2b080808, 0x0819192b2b2b2b2b, 0x08192b0808080819,
+    0x08192b0808081908, 0x08192b080808192b, 0x08192b0808082b19, 0x08192b0808190808,
+    0x08192b0808191919, 0x08192b0808192b08, 0x08192b08082b0819, 0x08192b0819080808,
+    0x08192b081908082b, 0x08192b0819081919, 0x08192b0819082b08, 0x08192b0819190819,
+    0x08192b0819191908, 0x08192b08192b0808, 0x08192b082b080819, 0x08192b082b081908,
+    0x08192b1908080808, 0x08192b190808082b, 0x08192b1908081919, 0x08192b1908082b08,
+    0x08192b1908190819, 0x08192b1908191908, 0x08192b19082b0808, 0x08192b1919080819,
+    0x08192b1919081908, 0x08192b1919190808, 0x08192b19192b2b19, 0x08192b192b2b082b,
+    0x08192b2b08081908, 0x08192b2b08190808, 0x08192b2b19080808, 0x08192b2b1919192b,
+    0x082b080808080808, 0x082b08080808082b, 0x082b080808081919, 0x082b080808082b08,
+    0x082b080808190819, 0x082b080808191908, 0x082b08080819192b, 0x082b080808192b19,
+    0x082b0808082b0808, 0x082b0808082b1919, 0x082b0808082b2b2b, 0x082b080819080819,
+    0x082b080819081908, 0x082b080819190808, 0x082b08081919082b, 0x082b080819191919,
+    0x082b0808192b1908, 0x082b08082b080808, 0x082b08082b082b2b, 0x082b08082b191908,
+    0x082b08082b2b2b2b, 0x082b081908080819, 0x082b081908081908, 0x082b081908190808,
+    0x082b08190819082b, 0x082b081908191919, 0x082b0819082b0819, 0x082b081919080808,
+    0x082b08191908082b, 0x082b081919081919, 0x082b081919190819, 0x082b081919191908,
+    0x082b0819192b0808, 0x082b08192b080819, 0x082b08192b081908, 0x082b08192b190808,
+    0x082b082b08080808, 0x082b082b08082b2b, 0x082b082b082b082b, 0x082b082b082b2b08,
+    0x082b082b082b2b2b, 0x082b082b19081908, 0x082b082b19190808, 0x082b082b2b082b08,
+    0x082b082b2b082b2b, 0x082b082b2b2b2b08, 0x082b190808080819, 0x082b190808081908,
+    0x082b19080808192b, 0x082b190808082b19, 0x082b190808190808, 0x082b190808191919,
+    0x082b190808192b08, 0x082b1908082b0819, 0x082b1908082b1908, 0x082b190819080808,
+    0x082b19081908082b, 0x082b190819081919, 0x082b190819082b08, 0x082b190819190819,
+    0x082b190819191908, 0x082b1908192b0808, 0x082b19082b080819, 0x082b19082b081908,
+    0x082b19082b190808, 0x082b191908080808, 0x082b191908081919, 0x082b191908082b08,
+    0x082b191908190819, 0x082b191908191908, 0x082b1919082b0808, 0x082b191919080819,
+    0x082b191919081908, 0x082b191919190808, 0x082b1919192b192b, 0x082b19192b080808,
+    0x082b192b08080819, 0x082b192b08081908, 0x082b192b08190808, 0x082b192b19080808,
+    0x082b192b19192b19, 0x082b2b0808080808, 0x082b2b0808081919, 0x082b2b0808190819,
+    0x082b2b0808191908, 0x082b2b0819080819, 0x082b2b0819081908, 0x082b2b0819190808,
+    0x082b2b082b082b2b, 0x082b2b082b2b2b2b, 0x082b2b1908080819, 0x082b2b1908081908,
+    0x082b2b1908190808, 0x082b2b192b191919, 0x082b2b2b08082b2b, 0x082b2b2b082b082b,
+    0x082b2b2b192b1908, 0x082b2b2b2b082b08, 0x082b2b2b2b082b2b, 0x1908080808080819,
+    0x1908080808081908, 0x190808080808192b, 0x1908080808082b19, 0x1908080808190808,
+    0x190808080819082b, 0x1908080808191919, 0x1908080808192b08, 0x1908080808192b2b,
+    0x19080808082b0819, 0x19080808082b1908, 0x19080808082b192b, 0x1908080819080808,
+    0x190808081908082b, 0x1908080819081919, 0x1908080819082b08, 0x1908080819082b2b,
+    0x1908080819190819, 0x1908080819191908, 0x190808081919192b, 0x1908080819192b19,
+    0x19080808192b0808, 0x19080808192b082b, 0x19080808192b1919, 0x190808082b080819,
+    0x190808082b081908, 0x190808082b190808, 0x190808082b191919, 0x190808082b192b08,
+    0x190808082b2b0819, 0x190808082b2b1908, 0x1908081908080808, 0x190808190808082b,
+    0x1908081908081919, 0x1908081908082b08, 0x1908081908190819, 0x1908081908191908,
+    0x190808190819192b, 0x1908081908192b19, 0x19080819082b0808, 0x19080819082b082b,
+    0x19080819082b1919, 0x1908081919080819, 0x1908081919081908, 0x190808191908192b,
+    0x1908081919082b19, 0x1908081919190808, 0x190808191919082b, 0x1908081919191919,
+    0x1908081919192b08, 0x19080819192b0819, 0x19080819192b1908, 0x190808192b080808,
+    0x190808192b08082b, 0x190808192b081919, 0x190808192b082b08, 0x190808192b190819,
+    0x190808192b191908, 0x190808192b2b0808, 0x1908082b08080819, 0x1908082b08081908,
+    0x1908082b08190808, 0x1908082b0819082b, 0x1908082b08191919, 0x1908082b08192b08,
+    0x1908082b082b1908, 0x1908082b19080808, 0x1908082b19081919, 0x1908082b19082b08,
+    0x1908082b19190819, 0x1908082b19191908, 0x1908082b192b0808, 0x1908082b2b080819,
+    0x1908082b2b081908, 0x1908190808080808, 0x190819080808082b, 0x1908190808081919,
+    0x1908190808082b08, 0x1908190808082b2b, 0x1908190808190819, 0x1908190808191908,
+    0x190819080819192b, 0x1908190808192b19, 0x19081908082b0808, 0x19081908082b082b,
+    0x19081908082b1919, 0x19081908082b2b08, 0x1908190819080819, 0x1908190819081908,
+    0x190819081908192b, 0x1908190819082b19, 0x1908190819190808, 0x190819081919082b,
+    0x1908190819191919, 0x1908190819192b08, 0x19081908192b0819, 0x19081908192b1908,
+    0x190819082b080808, 0x190819082b08082b, 0x190819082b081919, 0x190819082b082b08,
+    0x190819082b190819, 0x190819082b191908, 0x190819082b2b0808, 0x1908191908080819,
+    0x1908191908081908, 0x190819190808192b, 0x1908191908082b19, 0x1908191908190808,
+    0x190819190819082b, 0x1908191908191919, 0x1908191908192b08, 0x19081919082b0819,
+    0x19081919082b1908, 0x1908191919080808, 0x190819191908082b, 0x1908191919081919,
+    0x1908191919082b08, 0x1908191919190819, 0x1908191919191908, 0x19081919192b0808,
+    0x19081919192b2b2b, 0x190819192b080819, 0x190819192b081908, 0x190819192b190808,
+    0x1908192b08080808, 0x1908192b0808082b, 0x1908192b08081919, 0x1908192b08082b08,
+    0x1908192b08190819, 0x1908192b08191908, 0x1908192b082b0808, 0x1908192b19080819,
+    0x1908192b19081908, 0x1908192b19190808, 0x1908192b2b080808, 0x1908192b2b2b1919,
+    0x19082b0808080819, 0x19082b0808081908, 0x19082b0808082b19, 0x19082b0808190808,
+    0x19082b080819082b, 0x19082b0808191919, 0x19082b0808192b08, 0x19082b08082b0819,
+    0x19082b08082b1908, 0x19082b0819080808, 0x19082b081908082b, 0x19082b0819081919,
+    0x19082b0819082b08, 0x19082b0819190819, 0x19082b0819191908, 0x19082b08192b0808,
+    0x19082b082b081908, 0x19082b082b190808, 0x19082b1908080808, 0x19082b190808082b,
+    0x19082b1908081919, 0x19082b1908082b08, 0x19082b1908190819, 0x19082b1908191908,
+    0x19082b19082b0808, 0x19082b1919080819, 0x19082b1919081908, 0x19082b1919190808,
+    0x19082b192b080808, 0x19082b192b19192b, 0x19082b2b08080819, 0x19082b2b08081908,
+    0x19082b2b08190808, 0x19082b2b19080808, 0x1919080808080808, 0x191908080808082b,
+    0x1919080808081919, 0x1919080808082b08, 0x1919080808190819, 0x1919080808191908,
+    0x191908080819192b, 0x1919080808192b19, 0x19190808082b0808, 0x19190808082b082b,
+    0x19190808082b1919, 0x19190808082b2b08, 0x1919080819080819, 0x1919080819081908,
+    0x191908081908192b, 0x1919080819082b19, 0x1919080819190808, 0x191908081919082b,
+    0x1919080819191919, 0x1919080819192b08, 0x19190808192b0819, 0x19190808192b1908,
+    0x191908082b080808, 0x191908082b08082b, 0x191908082b081919, 0x191908082b082b08,
+    0x191908082b190819, 0x191908082b191908, 0x1919081908080819, 0x1919081908081908,
+    0x191908190808192b, 0x1919081908082b19, 0x1919081908190808, 0x191908190819082b,
+    0x1919081908191919, 0x1919081908192b08, 0x19190819082b0819, 0x19190819082b1908,
+    0x1919081919080808, 0x191908191908082b, 0x1919081919081919, 0x1919081919082b08,
+    0x1919081919190819, 0x1919081919191908, 0x19190819192b0808, 0x191908192b080819,
+    0x191908192b081908, 0x191908192b190808, 0x1919082b08080808, 0x1919082b08081919,
+    0x1919082b08082b08, 0x1919082b08190819, 0x1919082b08191908, 0x1919082b082b0808,
+    0x1919082b19080819, 0x1919082b19081908, 0x1919082b19190808, 0x1919082b192b2b19,
+    0x1919082b2b080808, 0x1919190808080819, 0x1919190808081908, 0x191919080808192b,
+    0x1919190808082b19, 0x1919190808190808, 0x191919080819082b, 0x1919190808191919,
+    0x1919190808192b08, 0x19191908082b0819, 0x19191908082b1908, 0x1919190819080808,
+    0x191919081908082b, 0x1919190819081919, 0x1919190819082b08, 0x1919190819190819,
+    0x1919190819191908, 0x19191908192b0808, 0x191919082b080819, 0x191919082b081908,
+    0x191919082b190808, 0x1919191908080808, 0x191919190808082b, 0x1919191908081919,
+    0x1919191908082b08, 0x1919191908190819, 0x1919191908191908, 0x19191919082b0808,
+    0x1919191919080819, 0x1919191919081908, 0x1919191919190808, 0x191919192b080808,
+    0x1919192b08080819, 0x1919192b08081908, 0x1919192b08190808, 0x1919192b082b192b,
+    0x1919192b19080808, 0x19192b0808080808, 0x19192b080808082b, 0x19192b0808081919,
+    0x19192b0808082b08, 0x19192b0808190819, 0x19192b0808191908, 0x19192b08082b0808,
+    0x19192b0819080819, 0x19192b0819081908, 0x19192b0819190808, 0x19192b0819192b2b,
+    0x19192b082b080808, 0x19192b1908080819, 0x19192b1908081908, 0x19192b1908190808,
+    0x19192b1919080808, 0x19192b2b08080808, 0x19192b2b08192b19, 0x19192b2b2b081919,
+    0x19192b2b2b2b2b08, 0x192b080808080819, 0x192b080808081908, 0x192b08080808192b,
+    0x192b080808190808, 0x192b08080819082b, 0x192b080808191919, 0x192b080808192b08,
+    0x192b0808082b0819, 0x192b0808082b1908, 0x192b080819080808, 0x192b080819081919,
+    0x192b080819082b08, 0x192b080819190819, 0x192b080819191908, 0x192b0808192b0808,
+    0x192b08082b081908, 0x192b08082b190808, 0x192b081908080808, 0x192b08190808082b,
+    0x192b081908081919, 0x192b081908082b08, 0x192b081908190819, 0x192b081908191908,
+    0x192b0819082b0808, 0x192b081919080819, 0x192b081919081908, 0x192b081919190808,
+    0x192b08192b080808, 0x192b08192b192b19, 0x192b082b08081908, 0x192b082b08190808,
+    0x192b082b19080808, 0x192b082b1919192b, 0x192b082b2b2b0819, 0x192b190808080808,
+    0x192b190808081919, 0x192b190808082b08, 0x192b190808190819, 0x192b190808191908,
+    0x192b1908082b0808, 0x192b190819080819, 0x192b190819081908, 0x192b190819190808,
+    0x192b19082b080808, 0x192b191908080819, 0x192b191908081908, 0x192b191908190808,
+    0x192b191919080808, 0x192b191919082b2b, 0x192b1919192b2b08, 0x192b19192b19082b,
+    0x192b192b08080808, 0x192b192b2b191908, 0x192b2b0808080819, 0x192b2b0808081908,
+    0x192b2b0808190808, 0x192b2b08192b1919, 0x192b2b082b192b08, 0x192b2b1908080808,
+    0x192b2b19082b2b2b, 0x192b2b2b1908082b, 0x192b2b2b2b2b0819, 0x2b08080808080808,
+    0x2b0808080808082b, 0x2b08080808081919, 0x2b08080808082b08, 0x2b08080808190819,
+    0x2b08080808191908, 0x2b08080808192b19, 0x2b080808082b0808, 0x2b080808082b1919,
+    0x2b08080819080819, 0x2b08080819081908, 0x2b08080819190808, 0x2b0808081919082b,
+    0x2b08080819191919, 0x2b08080819192b08, 0x2b080808192b0819, 0x2b0808082b080808,
+    0x2b0808082b081919, 0x2b0808082b190819, 0x2b0808082b191908, 0x2b08081908080819,
+    0x2b08081908081908, 0x2b08081908082b19, 0x2b08081908190808, 0x2b0808190819082b,
+    0x2b08081908191919, 0x2b08081908192b08, 0x2b080819082b0819, 0x2b080819082b1908,
+    0x2b08081919080808, 0x2b0808191908082b, 0x2b08081919081919, 0x2b08081919082b08,
+    0x2b08081919190819, 0x2b08081919191908, 0x2b0808192b080819, 0x2b0808192b081908,
+    0x2b0808192b190808, 0x2b0808192b2b2b19, 0x2b08082b08080808, 0x2b08082b08081919,
+    0x2b08082b08082b2b, 0x2b08082b08190819, 0x2b08082b08191908, 0x2b08082b19080819,
+    0x2b08082b19081908, 0x2b08082b19190808, 0x2b08190808080819, 0x2b08190808081908,
+    0x2b0819080808192b, 0x2b08190808082b19, 0x2b08190808190808, 0x2b0819080819082b,
+    0x2b08190808191919, 0x2b08190808192b08, 0x2b081908082b0819, 0x2b08190819080808,
+    0x2b0819081908082b, 0x2b08190819081919, 0x2b08190819082b08, 0x2b08190819190819,
+    0x2b08190819191908, 0x2b081908192b0808, 0x2b0819082b080819, 0x2b0819082b081908,
+    0x2b0819082b190808, 0x2b08191908080808, 0x2b0819190808082b, 0x2b08191908081919,
+    0x2b08191908082b08, 0x2b08191908190819, 0x2b08191908191908, 0x2b081919082b0808,
+    0x2b08191919080819, 0x2b08191919081908, 0x2b08191919190808, 0x2b0819192b080808,
+    0x2b0819192b082b2b, 0x2b08192b08080819, 0x2b08192b08081908, 0x2b08192b08190808,
+    0x2b08192b082b2b19, 0x2b08192b19080808, 0x2b082b0808080808, 0x2b082b0808081919,
+    0x2b082b0808190819, 0x2b082b0808191908, 0x2b082b0819080819, 0x2b082b0819081908,
+    0x2b082b0819190808, 0x2b082b082b2b082b, 0x2b082b1908080819, 0x2b082b1908081908,
+    0x2b082b1919080808, 0x2b082b19192b1919, 0x2b082b2b082b082b, 0x2b082b2b19192b08,
+    0x2b082b2b19192b2b, 0x2b082b2b2b08082b, 0x2b082b2b2b2b082b, 0x2b19080808080819,
+    0x2b19080808081908, 0x2b19080808082b19, 0x2b19080808190808, 0x2b1908080819082b,
+    0x2b19080808191919, 0x2b19080808192b08, 0x2b190808082b1908, 0x2b19080819080808,
+    0x2b1908081908082b, 0x2b19080819081919, 0x2b19080819082b08, 0x2b19080819190819,
+    0x2b19080819191908, 0x2b190808192b0808, 0x2b1908082b080819, 0x2b1908082b081908,
+    0x2b1908082b190808, 0x2b19081908080808, 0x2b19081908081919, 0x2b19081908190819,
+    0x2b19081908191908, 0x2b19081919080819, 0x2b19081919081908, 0x2b19081919190808,
+    0x2b19081919192b2b, 0x2b19082b08080819, 0x2b19082b08081908, 0x2b19082b08190808,
+    0x2b19082b19080808, 0x2b19082b2b2b192b, 0x2b19190808080808, 0x2b1919080808082b,
+    0x2b19190808081919, 0x2b19190808082b08, 0x2b19190808190819, 0x2b19190808191908,
+    0x2b191908082b0808, 0x2b19190819080819, 0x2b19190819081908, 0x2b19190819190808,
+    0x2b1919082b080808, 0x2b1919082b19192b, 0x2b19191908080819, 0x2b19191908081908,
+    0x2b19191908190808, 0x2b19191919080808, 0x2b1919192b192b08, 0x2b1919192b2b0819,
+    0x2b19192b08080808, 0x2b19192b1908192b, 0x2b19192b192b1908, 0x2b192b0808080819,
+    0x2b192b0808081908, 0x2b192b0808190808, 0x2b192b08082b192b, 0x2b192b0819080808,
+    0x2b192b082b2b2b19, 0x2b192b1908080808, 0x2b192b1919082b19, 0x2b192b191919082b,
+    0x2b192b2b2b190808, 0x2b2b080808080808, 0x2b2b080808081919, 0x2b2b080808082b2b,
+    0x2b2b080808191908, 0x2b2b0808082b082b, 0x2b2b0808082b2b2b, 0x2b2b080819080819,
+    0x2b2b080819081908, 0x2b2b080819190808, 0x2b2b08082b2b082b, 0x2b2b08082b2b2b2b,
+    0x2b2b081919080808, 0x2b2b0819192b1919, 0x2b2b082b0808082b, 0x2b2b082b08082b2b,
+    0x2b2b082b082b082b, 0x2b2b082b082b2b08, 0x2b2b082b082b2b2b, 0x2b2b082b2b08082b,
+    0x2b2b082b2b082b08, 0x2b2b082b2b082b2b, 0x2b2b082b2b2b2b08, 0x2b2b190808080819,
+    0x2b2b190808081908, 0x2b2b190808190808, 0x2b2b190819080808, 0x2b2b19082b082b19,
+    0x2b2b19082b2b1908, 0x2b2b191908080808, 0x2b2b191908192b19, 0x2b2b192b19190819,
+    0x2b2b2b0808082b2b, 0x2b2b2b08082b2b08, 0x2b2b2b082b2b082b, 0x2b2b2b1919191908,
+    0x2b2b2b192b08192b, 0x2b2b2b2b08082b08, 0x2b2b2b2b08082b2b, 0x2b2b2b2b082b0808,
+    0x2b2b2b2b082b082b, 0x2b2b2b2b082b2b08, 0x2b2b2b2b2b082b08, 0x2b2b2b2b2b2b2b2b,
+GGML_TABLE_END()
+
+GGML_TABLE_BEGIN(uint32_t, iq3xxs_grid, 256)
+    0x04040404, 0x04040414, 0x04040424, 0x04040c0c, 0x04040c1c, 0x04040c3e, 0x04041404, 0x04041414,
+    0x04041c0c, 0x04042414, 0x04043e1c, 0x04043e2c, 0x040c040c, 0x040c041c, 0x040c0c04, 0x040c0c14,
+    0x040c140c, 0x040c142c, 0x040c1c04, 0x040c1c14, 0x040c240c, 0x040c2c24, 0x040c3e04, 0x04140404,
+    0x04140414, 0x04140424, 0x04140c0c, 0x04141404, 0x04141414, 0x04141c0c, 0x04141c1c, 0x04141c3e,
+    0x04142c0c, 0x04142c3e, 0x04143e2c, 0x041c040c, 0x041c043e, 0x041c0c04, 0x041c0c14, 0x041c142c,
+    0x041c3e04, 0x04240c1c, 0x04241c3e, 0x04242424, 0x04242c3e, 0x04243e1c, 0x04243e2c, 0x042c040c,
+    0x042c043e, 0x042c1c14, 0x042c2c14, 0x04341c2c, 0x04343424, 0x043e0c04, 0x043e0c24, 0x043e0c34,
+    0x043e241c, 0x043e340c, 0x0c04040c, 0x0c04041c, 0x0c040c04, 0x0c040c14, 0x0c04140c, 0x0c04141c,
+    0x0c041c04, 0x0c041c14, 0x0c041c24, 0x0c04243e, 0x0c042c04, 0x0c0c0404, 0x0c0c0414, 0x0c0c0c0c,
+    0x0c0c1404, 0x0c0c1414, 0x0c14040c, 0x0c14041c, 0x0c140c04, 0x0c140c14, 0x0c14140c, 0x0c141c04,
+    0x0c143e14, 0x0c1c0404, 0x0c1c0414, 0x0c1c1404, 0x0c1c1c0c, 0x0c1c2434, 0x0c1c3434, 0x0c24040c,
+    0x0c24042c, 0x0c242c04, 0x0c2c1404, 0x0c2c1424, 0x0c2c2434, 0x0c2c3e0c, 0x0c34042c, 0x0c3e1414,
+    0x0c3e2404, 0x14040404, 0x14040414, 0x14040c0c, 0x14040c1c, 0x14041404, 0x14041414, 0x14041434,
+    0x14041c0c, 0x14042414, 0x140c040c, 0x140c041c, 0x140c042c, 0x140c0c04, 0x140c0c14, 0x140c140c,
+    0x140c1c04, 0x140c341c, 0x140c343e, 0x140c3e04, 0x14140404, 0x14140414, 0x14140c0c, 0x14140c3e,
+    0x14141404, 0x14141414, 0x14141c3e, 0x14142404, 0x14142c2c, 0x141c040c, 0x141c0c04, 0x141c0c24,
+    0x141c3e04, 0x141c3e24, 0x14241c2c, 0x14242c1c, 0x142c041c, 0x142c143e, 0x142c240c, 0x142c3e24,
+    0x143e040c, 0x143e041c, 0x143e0c34, 0x143e242c, 0x1c04040c, 0x1c040c04, 0x1c040c14, 0x1c04140c,
+    0x1c04141c, 0x1c042c04, 0x1c04342c, 0x1c043e14, 0x1c0c0404, 0x1c0c0414, 0x1c0c1404, 0x1c0c1c0c,
+    0x1c0c2424, 0x1c0c2434, 0x1c14040c, 0x1c14041c, 0x1c140c04, 0x1c14142c, 0x1c142c14, 0x1c143e14,
+    0x1c1c0c0c, 0x1c1c1c1c, 0x1c241c04, 0x1c24243e, 0x1c243e14, 0x1c2c0404, 0x1c2c0434, 0x1c2c1414,
+    0x1c2c2c2c, 0x1c340c24, 0x1c341c34, 0x1c34341c, 0x1c3e1c1c, 0x1c3e3404, 0x24040424, 0x24040c3e,
+    0x24041c2c, 0x24041c3e, 0x24042c1c, 0x24042c3e, 0x240c3e24, 0x24141404, 0x24141c3e, 0x24142404,
+    0x24143404, 0x24143434, 0x241c043e, 0x241c242c, 0x24240424, 0x24242c0c, 0x24243424, 0x242c142c,
+    0x242c241c, 0x242c3e04, 0x243e042c, 0x243e0c04, 0x243e0c14, 0x243e1c04, 0x2c040c14, 0x2c04240c,
+    0x2c043e04, 0x2c0c0404, 0x2c0c0434, 0x2c0c1434, 0x2c0c2c2c, 0x2c140c24, 0x2c141c14, 0x2c143e14,
+    0x2c1c0414, 0x2c1c2c1c, 0x2c240c04, 0x2c24141c, 0x2c24143e, 0x2c243e14, 0x2c2c0414, 0x2c2c1c0c,
+    0x2c342c04, 0x2c3e1424, 0x2c3e2414, 0x34041424, 0x34042424, 0x34042434, 0x34043424, 0x340c140c,
+    0x340c340c, 0x34140c3e, 0x34143424, 0x341c1c04, 0x341c1c34, 0x34242424, 0x342c042c, 0x342c2c14,
+    0x34341c1c, 0x343e041c, 0x343e140c, 0x3e04041c, 0x3e04042c, 0x3e04043e, 0x3e040c04, 0x3e041c14,
+    0x3e042c14, 0x3e0c1434, 0x3e0c2404, 0x3e140c14, 0x3e14242c, 0x3e142c14, 0x3e1c0404, 0x3e1c0c2c,
+    0x3e1c1c1c, 0x3e1c3404, 0x3e24140c, 0x3e24240c, 0x3e2c0404, 0x3e2c0414, 0x3e2c1424, 0x3e341c04,
+GGML_TABLE_END()
+
+GGML_TABLE_BEGIN(uint32_t, iq3s_grid, 512)
+    0x01010101, 0x01010103, 0x01010105, 0x0101010b, 0x0101010f, 0x01010301, 0x01010303, 0x01010305,
+    0x01010309, 0x0101030d, 0x01010501, 0x01010503, 0x0101050b, 0x01010707, 0x01010901, 0x01010905,
+    0x0101090b, 0x0101090f, 0x01010b03, 0x01010b07, 0x01010d01, 0x01010d05, 0x01010f03, 0x01010f09,
+    0x01010f0f, 0x01030101, 0x01030103, 0x01030105, 0x01030109, 0x01030301, 0x01030303, 0x0103030b,
+    0x01030501, 0x01030507, 0x0103050f, 0x01030703, 0x0103070b, 0x01030909, 0x01030d03, 0x01030d0b,
+    0x01030f05, 0x01050101, 0x01050103, 0x0105010b, 0x0105010f, 0x01050301, 0x01050307, 0x0105030d,
+    0x01050503, 0x0105050b, 0x01050701, 0x01050709, 0x01050905, 0x0105090b, 0x0105090f, 0x01050b03,
+    0x01050b07, 0x01050f01, 0x01050f07, 0x01070107, 0x01070303, 0x0107030b, 0x01070501, 0x01070505,
+    0x01070703, 0x01070707, 0x0107070d, 0x01070909, 0x01070b01, 0x01070b05, 0x01070d0f, 0x01070f03,
+    0x01070f0b, 0x01090101, 0x01090307, 0x0109030f, 0x01090503, 0x01090509, 0x01090705, 0x01090901,
+    0x01090907, 0x01090b03, 0x01090f01, 0x010b0105, 0x010b0109, 0x010b0501, 0x010b0505, 0x010b050d,
+    0x010b0707, 0x010b0903, 0x010b090b, 0x010b090f, 0x010b0d0d, 0x010b0f07, 0x010d010d, 0x010d0303,
+    0x010d0307, 0x010d0703, 0x010d0b05, 0x010d0f03, 0x010f0101, 0x010f0105, 0x010f0109, 0x010f0501,
+    0x010f0505, 0x010f050d, 0x010f0707, 0x010f0b01, 0x010f0b09, 0x03010101, 0x03010103, 0x03010105,
+    0x03010109, 0x03010301, 0x03010303, 0x03010307, 0x0301030b, 0x0301030f, 0x03010501, 0x03010505,
+    0x03010703, 0x03010709, 0x0301070d, 0x03010b09, 0x03010b0d, 0x03010d03, 0x03010f05, 0x03030101,
+    0x03030103, 0x03030107, 0x0303010d, 0x03030301, 0x03030309, 0x03030503, 0x03030701, 0x03030707,
+    0x03030903, 0x03030b01, 0x03030b05, 0x03030f01, 0x03030f0d, 0x03050101, 0x03050305, 0x0305030b,
+    0x0305030f, 0x03050501, 0x03050509, 0x03050705, 0x03050901, 0x03050907, 0x03050b0b, 0x03050d01,
+    0x03050f05, 0x03070103, 0x03070109, 0x0307010f, 0x03070301, 0x03070307, 0x03070503, 0x0307050f,
+    0x03070701, 0x03070709, 0x03070903, 0x03070d05, 0x03070f01, 0x03090107, 0x0309010b, 0x03090305,
+    0x03090309, 0x03090703, 0x03090707, 0x03090905, 0x0309090d, 0x03090b01, 0x03090b09, 0x030b0103,
+    0x030b0301, 0x030b0307, 0x030b0503, 0x030b0701, 0x030b0705, 0x030b0b03, 0x030d0501, 0x030d0509,
+    0x030d050f, 0x030d0909, 0x030d090d, 0x030f0103, 0x030f0107, 0x030f0301, 0x030f0305, 0x030f0503,
+    0x030f070b, 0x030f0903, 0x030f0d05, 0x030f0f01, 0x05010101, 0x05010103, 0x05010107, 0x0501010b,
+    0x0501010f, 0x05010301, 0x05010305, 0x05010309, 0x0501030d, 0x05010503, 0x05010507, 0x0501050f,
+    0x05010701, 0x05010705, 0x05010903, 0x05010907, 0x0501090b, 0x05010b01, 0x05010b05, 0x05010d0f,
+    0x05010f01, 0x05010f07, 0x05010f0b, 0x05030101, 0x05030105, 0x05030301, 0x05030307, 0x0503030f,
+    0x05030505, 0x0503050b, 0x05030703, 0x05030709, 0x05030905, 0x05030b03, 0x05050103, 0x05050109,
+    0x0505010f, 0x05050503, 0x05050507, 0x05050701, 0x0505070f, 0x05050903, 0x05050b07, 0x05050b0f,
+    0x05050f03, 0x05050f09, 0x05070101, 0x05070105, 0x0507010b, 0x05070303, 0x05070505, 0x05070509,
+    0x05070703, 0x05070707, 0x05070905, 0x05070b01, 0x05070d0d, 0x05090103, 0x0509010f, 0x05090501,
+    0x05090507, 0x05090705, 0x0509070b, 0x05090903, 0x05090f05, 0x05090f0b, 0x050b0109, 0x050b0303,
+    0x050b0505, 0x050b070f, 0x050b0901, 0x050b0b07, 0x050b0f01, 0x050d0101, 0x050d0105, 0x050d010f,
+    0x050d0503, 0x050d0b0b, 0x050d0d03, 0x050f010b, 0x050f0303, 0x050f050d, 0x050f0701, 0x050f0907,
+    0x050f0b01, 0x07010105, 0x07010303, 0x07010307, 0x0701030b, 0x0701030f, 0x07010505, 0x07010703,
+    0x07010707, 0x0701070b, 0x07010905, 0x07010909, 0x0701090f, 0x07010b03, 0x07010d07, 0x07010f03,
+    0x07030103, 0x07030107, 0x0703010b, 0x07030309, 0x07030503, 0x07030507, 0x07030901, 0x07030d01,
+    0x07030f05, 0x07030f0d, 0x07050101, 0x07050305, 0x07050501, 0x07050705, 0x07050709, 0x07050b01,
+    0x07070103, 0x07070301, 0x07070309, 0x07070503, 0x07070507, 0x0707050f, 0x07070701, 0x07070903,
+    0x07070907, 0x0707090f, 0x07070b0b, 0x07070f07, 0x07090107, 0x07090303, 0x0709030d, 0x07090505,
+    0x07090703, 0x07090b05, 0x07090d01, 0x07090d09, 0x070b0103, 0x070b0301, 0x070b0305, 0x070b050b,
+    0x070b0705, 0x070b0909, 0x070b0b0d, 0x070b0f07, 0x070d030d, 0x070d0903, 0x070f0103, 0x070f0107,
+    0x070f0501, 0x070f0505, 0x070f070b, 0x09010101, 0x09010109, 0x09010305, 0x09010501, 0x09010509,
+    0x0901050f, 0x09010705, 0x09010903, 0x09010b01, 0x09010f01, 0x09030105, 0x0903010f, 0x09030303,
+    0x09030307, 0x09030505, 0x09030701, 0x0903070b, 0x09030907, 0x09030b03, 0x09030b0b, 0x09050103,
+    0x09050107, 0x09050301, 0x0905030b, 0x09050503, 0x09050707, 0x09050901, 0x09050b0f, 0x09050d05,
+    0x09050f01, 0x09070109, 0x09070303, 0x09070307, 0x09070501, 0x09070505, 0x09070703, 0x0907070b,
+    0x09090101, 0x09090105, 0x09090509, 0x0909070f, 0x09090901, 0x09090f03, 0x090b010b, 0x090b010f,
+    0x090b0503, 0x090b0d05, 0x090d0307, 0x090d0709, 0x090d0d01, 0x090f0301, 0x090f030b, 0x090f0701,
+    0x090f0907, 0x090f0b03, 0x0b010105, 0x0b010301, 0x0b010309, 0x0b010505, 0x0b010901, 0x0b010909,
+    0x0b01090f, 0x0b010b05, 0x0b010d0d, 0x0b010f09, 0x0b030103, 0x0b030107, 0x0b03010b, 0x0b030305,
+    0x0b030503, 0x0b030705, 0x0b030f05, 0x0b050101, 0x0b050303, 0x0b050507, 0x0b050701, 0x0b05070d,
+    0x0b050b07, 0x0b070105, 0x0b07010f, 0x0b070301, 0x0b07050f, 0x0b070909, 0x0b070b03, 0x0b070d0b,
+    0x0b070f07, 0x0b090103, 0x0b090109, 0x0b090501, 0x0b090705, 0x0b09090d, 0x0b0b0305, 0x0b0b050d,
+    0x0b0b0b03, 0x0b0b0b07, 0x0b0d0905, 0x0b0f0105, 0x0b0f0109, 0x0b0f0505, 0x0d010303, 0x0d010307,
+    0x0d01030b, 0x0d010703, 0x0d010707, 0x0d010d01, 0x0d030101, 0x0d030501, 0x0d03050f, 0x0d030d09,
+    0x0d050305, 0x0d050709, 0x0d050905, 0x0d050b0b, 0x0d050d05, 0x0d050f01, 0x0d070101, 0x0d070309,
+    0x0d070503, 0x0d070901, 0x0d09050b, 0x0d090907, 0x0d090d05, 0x0d0b0101, 0x0d0b0107, 0x0d0b0709,
+    0x0d0b0d01, 0x0d0d010b, 0x0d0d0901, 0x0d0f0303, 0x0d0f0307, 0x0f010101, 0x0f010109, 0x0f01010f,
+    0x0f010501, 0x0f010505, 0x0f01070d, 0x0f010901, 0x0f010b09, 0x0f010d05, 0x0f030105, 0x0f030303,
+    0x0f030509, 0x0f030907, 0x0f03090b, 0x0f050103, 0x0f050109, 0x0f050301, 0x0f05030d, 0x0f050503,
+    0x0f050701, 0x0f050b03, 0x0f070105, 0x0f070705, 0x0f07070b, 0x0f070b07, 0x0f090103, 0x0f09010b,
+    0x0f090307, 0x0f090501, 0x0f090b01, 0x0f0b0505, 0x0f0b0905, 0x0f0d0105, 0x0f0d0703, 0x0f0f0101,
+GGML_TABLE_END()
+
+#define NGRID_IQ1S 2048
+#if defined(GGML_COMMON_IMPL_C)
+GGML_TABLE_BEGIN(uint64_t, iq1s_grid, NGRID_IQ1S)
+    0xffffffffffffffff, 0xffffffffffffff01, 0xffffffffffff0000, 0xffffffffffff01ff,
+    0xffffffffffff0101, 0xffffffffff00ff00, 0xffffffffff000000, 0xffffffffff01ffff,
+    0xffffffffff01ff01, 0xffffffffff0101ff, 0xffffffffff010101, 0xffffffff00ff0000,
+    0xffffffff0000ff00, 0xffffffff000000ff, 0xffffffff00000001, 0xffffffff00010000,
+    0xffffffff01ffffff, 0xffffffff01ffff01, 0xffffffff01ff01ff, 0xffffffff01ff0101,
+    0xffffffff01000000, 0xffffffff0101ffff, 0xffffffff0101ff01, 0xffffffff010101ff,
+    0xffffffff01010101, 0xffffff00ffff00ff, 0xffffff00ffff0000, 0xffffff00ff00ff00,
+    0xffffff00ff0000ff, 0xffffff00ff000001, 0xffffff00ff000100, 0xffffff00ff000101,
+    0xffffff00ff010000, 0xffffff0000ffff00, 0xffffff0000ff0001, 0xffffff0000ff0100,
+    0xffffff000000ff01, 0xffffff0000000000, 0xffffff0000000101, 0xffffff000001ff00,
+    0xffffff00000100ff, 0xffffff0000010001, 0xffffff00000101ff, 0xffffff0001ff0000,
+    0xffffff000100ff00, 0xffffff00010000ff, 0xffffff0001000001, 0xffffff0001010000,
+    0xffffff01ffffffff, 0xffffff01ffffff01, 0xffffff01ffff01ff, 0xffffff01ffff0101,
+    0xffffff01ff000000, 0xffffff01ff01ffff, 0xffffff01ff01ff01, 0xffffff01ff0101ff,
+    0xffffff01ff010101, 0xffffff0100ff0000, 0xffffff010000ff00, 0xffffff0100000100,
+    0xffffff01000100ff, 0xffffff0100010100, 0xffffff0101ffffff, 0xffffff0101ffff01,
+    0xffffff0101ff01ff, 0xffffff0101ff0101, 0xffffff010100ff00, 0xffffff0101000000,
+    0xffffff0101000100, 0xffffff010101ffff, 0xffffff010101ff01, 0xffffff01010101ff,
+    0xffffff0101010101, 0xffff00ffff00ff00, 0xffff00ffff0000ff, 0xffff00ffff000001,
+    0xffff00ffff010000, 0xffff00ff00ffff00, 0xffff00ff00ff0100, 0xffff00ff00000000,
+    0xffff00ff00000101, 0xffff00ff000100ff, 0xffff00ff00010000, 0xffff00ff0100ff00,
+    0xffff00ff01000100, 0xffff00ff01010000, 0xffff0000ffffff00, 0xffff0000ffff00ff,
+    0xffff0000ffff0000, 0xffff0000ffff0001, 0xffff0000ff000000, 0xffff0000ff0001ff,
+    0xffff0000ff000101, 0xffff0000ff010100, 0xffff000000ffffff, 0xffff000000ff0000,
+    0xffff000000ff0101, 0xffff00000000ffff, 0xffff00000000ff00, 0xffff0000000000ff,
+    0xffff000000000000, 0xffff000000000001, 0xffff000000000100, 0xffff00000001ffff,
+    0xffff00000001ff01, 0xffff000000010000, 0xffff0000000101ff, 0xffff000000010101,
+    0xffff000001ffff00, 0xffff00000100ff00, 0xffff000001000000, 0xffff0000010001ff,
+    0xffff000001000101, 0xffff00000101ff00, 0xffff0000010100ff, 0xffff000001010000,
+    0xffff000001010001, 0xffff000001010100, 0xffff0001ff0000ff, 0xffff0001ff000100,
+    0xffff000100ffff00, 0xffff000100ff00ff, 0xffff00010000ffff, 0xffff00010000ff01,
+    0xffff000100000000, 0xffff0001000001ff, 0xffff00010001ffff, 0xffff00010001ff00,
+    0xffff000100010001, 0xffff000100010100, 0xffff000101ff0000, 0xffff00010100ff00,
+    0xffff0001010000ff, 0xffff000101000100, 0xffff01ffffffffff, 0xffff01ffffffff01,
+    0xffff01ffffff01ff, 0xffff01ffffff0101, 0xffff01ffff000000, 0xffff01ffff01ffff,
+    0xffff01ffff01ff01, 0xffff01ffff0101ff, 0xffff01ffff010101, 0xffff01ff00ff0000,
+    0xffff01ff0000ff00, 0xffff01ff00000001, 0xffff01ff00010000, 0xffff01ff01ffffff,
+    0xffff01ff01ffff01, 0xffff01ff01ff01ff, 0xffff01ff01ff0101, 0xffff01ff01000000,
+    0xffff01ff0101ffff, 0xffff01ff0101ff01, 0xffff01ff010101ff, 0xffff01ff01010101,
+    0xffff0100ffff0000, 0xffff0100ff00ff00, 0xffff0100ff0000ff, 0xffff0100ff000100,
+    0xffff0100ff0100ff, 0xffff0100ff010000, 0xffff010000ffff00, 0xffff01000000ffff,
+    0xffff01000000ff00, 0xffff010000000000, 0xffff01000001ff00, 0xffff0100000100ff,
+    0xffff010000010100, 0xffff01000100ff00, 0xffff0100010000ff, 0xffff010001000001,
+    0xffff010001000100, 0xffff010001010000, 0xffff0101ffffffff, 0xffff0101ffffff01,
+    0xffff0101ffff01ff, 0xffff0101ffff0101, 0xffff0101ff000000, 0xffff0101ff01ffff,
+    0xffff0101ff01ff01, 0xffff0101ff0101ff, 0xffff0101ff010101, 0xffff010100ff0000,
+    0xffff01010000ff00, 0xffff010100000100, 0xffff01010001ff00, 0xffff010100010000,
+    0xffff010101ffffff, 0xffff010101ffff01, 0xffff010101ff0000, 0xffff010101ff01ff,
+    0xffff010101ff0101, 0xffff010101000000, 0xffff01010101ffff, 0xffff01010101ff01,
+    0xffff0101010101ff, 0xffff010101010101, 0xff00ffffff00ffff, 0xff00ffffff00ff00,
+    0xff00ffffff0000ff, 0xff00ffffff000100, 0xff00ffffff0100ff, 0xff00ffffff010000,
+    0xff00ffff00ffff00, 0xff00ffff00ff00ff, 0xff00ffff0000ffff, 0xff00ffff00000000,
+    0xff00ffff000001ff, 0xff00ffff0001ff00, 0xff00ffff000100ff, 0xff00ffff00010000,
+    0xff00ffff00010100, 0xff00ffff0100ff00, 0xff00ffff010000ff, 0xff00ffff01000001,
+    0xff00ffff0101ff00, 0xff00ffff01010000, 0xff00ff00ffffff00, 0xff00ff00ffff00ff,
+    0xff00ff00ffff0001, 0xff00ff00ffff0100, 0xff00ff00ff00ffff, 0xff00ff00ff00ff01,
+    0xff00ff00ff000000, 0xff00ff00ff0001ff, 0xff00ff00ff01ff00, 0xff00ff00ff0100ff,
+    0xff00ff00ff010100, 0xff00ff0000ff0000, 0xff00ff0000ff0101, 0xff00ff000000ffff,
+    0xff00ff000000ff00, 0xff00ff000000ff01, 0xff00ff00000000ff, 0xff00ff0000000000,
+    0xff00ff0000000001, 0xff00ff0000000100, 0xff00ff000001ffff, 0xff00ff0000010000,
+    0xff00ff0001ff00ff, 0xff00ff000100ff01, 0xff00ff0001000000, 0xff00ff000101ff00,
+    0xff00ff00010100ff, 0xff00ff01ff00ff00, 0xff00ff01ff0000ff, 0xff00ff01ff000001,
+    0xff00ff01ff010000, 0xff00ff0100ffffff, 0xff00ff0100ff0001, 0xff00ff0100ff0100,
+    0xff00ff010000ff01, 0xff00ff0100000000, 0xff00ff01000001ff, 0xff00ff0100000101,
+    0xff00ff01000100ff, 0xff00ff0100010001, 0xff00ff0101ff0000, 0xff00ff010100ff00,
+    0xff00ff01010000ff, 0xff00ff0101000001, 0xff00ff0101010000, 0xff0000ffffffff00,
+    0xff0000ffffff0001, 0xff0000ffffff0100, 0xff0000ffff0000ff, 0xff0000ffff000000,
+    0xff0000ffff0001ff, 0xff0000ffff000100, 0xff0000ffff01ff00, 0xff0000ffff010001,
+    0xff0000ff00ffff00, 0xff0000ff00ff0000, 0xff0000ff00ff0001, 0xff0000ff00ff01ff,
+    0xff0000ff00ff0101, 0xff0000ff0000ff00, 0xff0000ff000000ff, 0xff0000ff00000000,
+    0xff0000ff00000001, 0xff0000ff00000100, 0xff0000ff0001ff01, 0xff0000ff00010000,
+    0xff0000ff000101ff, 0xff0000ff01ff00ff, 0xff0000ff01ff0100, 0xff0000ff0100ffff,
+    0xff0000ff010000ff, 0xff0000ff01000000, 0xff0000ff010001ff, 0xff0000ff01000100,
+    0xff0000ff01000101, 0xff0000ff0101ff00, 0xff0000ff010100ff, 0xff0000ff01010000,
+    0xff0000ff01010100, 0xff000000ffffff01, 0xff000000ffff0000, 0xff000000ffff0101,
+    0xff000000ff00ff00, 0xff000000ff0000ff, 0xff000000ff000000, 0xff000000ff000001,
+    0xff000000ff000100, 0xff000000ff01ffff, 0xff000000ff01ff01, 0xff000000ff010000,
+    0xff000000ff0101ff, 0xff000000ff010101, 0xff00000000ffff00, 0xff00000000ff00ff,
+    0xff00000000ff0000, 0xff00000000ff0001, 0xff0000000000ff00, 0xff0000000000ff01,
+    0xff000000000000ff, 0xff00000000000000, 0xff00000000000001, 0xff00000000000100,
+    0xff00000000000101, 0xff0000000001ff00, 0xff000000000100ff, 0xff00000000010000,
+    0xff00000000010001, 0xff00000000010100, 0xff00000001ffffff, 0xff00000001ffff01,
+    0xff00000001ff00ff, 0xff00000001ff0000, 0xff00000001ff01ff, 0xff00000001ff0101,
+    0xff0000000100ffff, 0xff0000000100ff00, 0xff000000010000ff, 0xff00000001000000,
+    0xff00000001000001, 0xff00000001000100, 0xff00000001000101, 0xff0000000101ffff,
+    0xff0000000101ff01, 0xff00000001010000, 0xff000001ffffff00, 0xff000001ffff00ff,
+    0xff000001ffff0000, 0xff000001ffff0001, 0xff000001ff000000, 0xff000001ff000001,
+    0xff000001ff0001ff, 0xff000001ff000101, 0xff000001ff01ff00, 0xff000001ff010001,
+    0xff00000100ffffff, 0xff00000100ffff01, 0xff00000100ff00ff, 0xff00000100ff0000,
+    0xff00000100ff01ff, 0xff00000100ff0101, 0xff0000010000ff00, 0xff00000100000000,
+    0xff00000100000001, 0xff000001000001ff, 0xff00000100000100, 0xff0000010001ff00,
+    0xff000001000100ff, 0xff00000100010000, 0xff000001000101ff, 0xff00000100010100,
+    0xff00000100010101, 0xff00000101ff0001, 0xff00000101ff0101, 0xff0000010100ff01,
+    0xff00000101000000, 0xff000001010100ff, 0xff00000101010100, 0xff0001ffff00ff00,
+    0xff0001ffff000001, 0xff0001ffff010000, 0xff0001ff00ffff00, 0xff0001ff00ff00ff,
+    0xff0001ff00ff0001, 0xff0001ff00ff0100, 0xff0001ff0000ffff, 0xff0001ff00000000,
+    0xff0001ff000001ff, 0xff0001ff00000101, 0xff0001ff0001ffff, 0xff0001ff0001ff00,
+    0xff0001ff000100ff, 0xff0001ff00010001, 0xff0001ff00010100, 0xff0001ff01ff0000,
+    0xff0001ff0100ff00, 0xff0001ff010000ff, 0xff0001ff01010000, 0xff000100ff00ffff,
+    0xff000100ff00ff01, 0xff000100ff000000, 0xff000100ff000101, 0xff000100ff01ff00,
+    0xff000100ff010000, 0xff00010000ffff01, 0xff00010000ff00ff, 0xff00010000ff0000,
+    0xff00010000ff01ff, 0xff0001000000ff00, 0xff000100000000ff, 0xff00010000000000,
+    0xff00010000000001, 0xff00010000000100, 0xff00010000000101, 0xff0001000001ffff,
+    0xff00010000010000, 0xff00010000010101, 0xff00010001ff0100, 0xff0001000100ff00,
+    0xff0001000100ff01, 0xff00010001000000, 0xff000100010001ff, 0xff0001000101ff00,
+    0xff00010001010001, 0xff00010001010100, 0xff000101ffff0100, 0xff000101ff000001,
+    0xff000101ff0100ff, 0xff000101ff010001, 0xff00010100ff00ff, 0xff00010100ff0001,
+    0xff00010100ff0100, 0xff0001010000ffff, 0xff0001010000ff01, 0xff00010100000000,
+    0xff000101000001ff, 0xff0001010001ff00, 0xff00010100010001, 0xff00010100010100,
+    0xff00010101ff0000, 0xff0001010100ff00, 0xff00010101000001, 0xff00010101000101,
+    0xff01ffffffffffff, 0xff01ffffffffff01, 0xff01ffffffff01ff, 0xff01ffffffff0101,
+    0xff01ffffff000000, 0xff01ffffff01ffff, 0xff01ffffff01ff01, 0xff01ffffff010000,
+    0xff01ffffff0101ff, 0xff01ffffff010101, 0xff01ffff00ff0000, 0xff01ffff0000ff00,
+    0xff01ffff00000100, 0xff01ffff0001ff00, 0xff01ffff00010000, 0xff01ffff01ffffff,
+    0xff01ffff01ffff01, 0xff01ffff01ff01ff, 0xff01ffff01ff0101, 0xff01ffff01000000,
+    0xff01ffff0101ffff, 0xff01ffff0101ff01, 0xff01ffff01010000, 0xff01ffff010101ff,
+    0xff01ffff01010101, 0xff01ff00ffff0000, 0xff01ff00ff00ff00, 0xff01ff00ff0000ff,
+    0xff01ff00ff000100, 0xff01ff00ff010000, 0xff01ff0000ffff01, 0xff01ff0000ff00ff,
+    0xff01ff0000ff0100, 0xff01ff0000000000, 0xff01ff00000001ff, 0xff01ff0000000101,
+    0xff01ff000001ff00, 0xff01ff00000100ff, 0xff01ff0000010000, 0xff01ff0000010001,
+    0xff01ff0001ff0000, 0xff01ff000100ffff, 0xff01ff0001000001, 0xff01ff0001000100,
+    0xff01ff0001010000, 0xff01ff01ffffff00, 0xff01ff01ffff01ff, 0xff01ff01ffff0101,
+    0xff01ff01ff00ff00, 0xff01ff01ff000000, 0xff01ff01ff01ffff, 0xff01ff01ff01ff01,
+    0xff01ff01ff0101ff, 0xff01ff01ff010101, 0xff01ff0100ff0000, 0xff01ff010000ff00,
+    0xff01ff0100000001, 0xff01ff0100000100, 0xff01ff0100010000, 0xff01ff0101ffff00,
+    0xff01ff0101ff01ff, 0xff01ff0101ff0101, 0xff01ff010100ff00, 0xff01ff0101000000,
+    0xff01ff010101ffff, 0xff01ff010101ff01, 0xff01ff01010101ff, 0xff01ff0101010101,
+    0xff0100ffffff0000, 0xff0100ffff0000ff, 0xff0100ffff000001, 0xff0100ffff000100,
+    0xff0100ffff010000, 0xff0100ff00ff00ff, 0xff0100ff00ff0000, 0xff0100ff00ff0001,
+    0xff0100ff00ff0100, 0xff0100ff0000ff01, 0xff0100ff00000000, 0xff0100ff000001ff,
+    0xff0100ff00000101, 0xff0100ff00010001, 0xff0100ff01ff0000, 0xff0100ff0100ff00,
+    0xff0100ff010000ff, 0xff0100ff01000100, 0xff0100ff0101ff00, 0xff0100ff01010000,
+    0xff010000ffff0100, 0xff010000ff000000, 0xff010000ff01ff00, 0xff010000ff010100,
+    0xff01000000ffffff, 0xff01000000ff0000, 0xff01000000ff01ff, 0xff0100000000ff00,
+    0xff010000000000ff, 0xff01000000000000, 0xff01000000000100, 0xff0100000001ff01,
+    0xff01000000010000, 0xff010000000101ff, 0xff01000001ff0100, 0xff0100000100ffff,
+    0xff010000010000ff, 0xff01000001000000, 0xff010000010001ff, 0xff01000001000101,
+    0xff0100000101ff00, 0xff010000010100ff, 0xff01000001010001, 0xff01000001010100,
+    0xff010001ffff0000, 0xff010001ff00ffff, 0xff010001ff00ff01, 0xff010001ff000100,
+    0xff010001ff010000, 0xff01000100ffff00, 0xff01000100ff0100, 0xff01000100000000,
+    0xff0100010001ffff, 0xff0100010001ff00, 0xff01000100010100, 0xff01000101ff00ff,
+    0xff01000101ff0001, 0xff0100010100ffff, 0xff01000101000101, 0xff0101ffffffffff,
+    0xff0101ffffffff01, 0xff0101ffffff01ff, 0xff0101ffffff0101, 0xff0101ffff000000,
+    0xff0101ffff01ffff, 0xff0101ffff01ff01, 0xff0101ffff0101ff, 0xff0101ffff010101,
+    0xff0101ff00ff0000, 0xff0101ff0000ff00, 0xff0101ff000000ff, 0xff0101ff00010000,
+    0xff0101ff01ffffff, 0xff0101ff01ffff01, 0xff0101ff01ff01ff, 0xff0101ff01ff0101,
+    0xff0101ff0101ffff, 0xff0101ff0101ff01, 0xff0101ff010101ff, 0xff0101ff01010101,
+    0xff010100ffff0100, 0xff010100ff00ff00, 0xff010100ff0000ff, 0xff010100ff000100,
+    0xff010100ff010000, 0xff01010000ff0001, 0xff01010000ff0100, 0xff0101000000ff01,
+    0xff01010000000000, 0xff0101000001ff00, 0xff010100000100ff, 0xff01010000010001,
+    0xff01010000010100, 0xff01010001ff0000, 0xff0101000100ffff, 0xff01010001000001,
+    0xff01010001000100, 0xff010100010100ff, 0xff01010001010000, 0xff010101ffffffff,
+    0xff010101ffffff01, 0xff010101ffff01ff, 0xff010101ffff0101, 0xff010101ff01ffff,
+    0xff010101ff01ff01, 0xff010101ff0101ff, 0xff010101ff010101, 0xff01010100ff0000,
+    0xff0101010000ff00, 0xff01010100000001, 0xff01010100000100, 0xff01010100010000,
+    0xff01010101ffffff, 0xff01010101ffff01, 0xff01010101ff01ff, 0xff01010101ff0101,
+    0xff01010101000000, 0xff0101010101ffff, 0xff0101010101ff01, 0xff010101010101ff,
+    0xff01010101010101, 0x00ffffffffff0000, 0x00ffffffff00ff00, 0x00ffffffff000001,
+    0x00ffffffff010000, 0x00ffffff00ff0100, 0x00ffffff0000ff01, 0x00ffffff00000000,
+    0x00ffffff000001ff, 0x00ffffff00000101, 0x00ffffff0001ff00, 0x00ffffff000100ff,
+    0x00ffffff00010001, 0x00ffffff010000ff, 0x00ffffff01000100, 0x00ffffff0101ff00,
+    0x00ffffff01010001, 0x00ffff00ffffffff, 0x00ffff00ffffff00, 0x00ffff00ffff00ff,
+    0x00ffff00ffff0001, 0x00ffff00ffff0100, 0x00ffff00ff00ff01, 0x00ffff00ff000000,
+    0x00ffff00ff000001, 0x00ffff00ff0001ff, 0x00ffff00ff000101, 0x00ffff00ff01ff00,
+    0x00ffff00ff010001, 0x00ffff00ff010100, 0x00ffff0000ff0000, 0x00ffff0000ff01ff,
+    0x00ffff0000ff0101, 0x00ffff000000ff00, 0x00ffff00000000ff, 0x00ffff0000000000,
+    0x00ffff0000000001, 0x00ffff0000000100, 0x00ffff0000000101, 0x00ffff0000010000,
+    0x00ffff00000101ff, 0x00ffff0000010101, 0x00ffff0001ffff00, 0x00ffff0001ff00ff,
+    0x00ffff0001ff0001, 0x00ffff000100ffff, 0x00ffff000100ff01, 0x00ffff0001000000,
+    0x00ffff000101ffff, 0x00ffff000101ff00, 0x00ffff000101ff01, 0x00ffff01ffff0000,
+    0x00ffff01ff00ff00, 0x00ffff01ff0000ff, 0x00ffff01ff000001, 0x00ffff01ff010000,
+    0x00ffff0100ffff00, 0x00ffff010000ff01, 0x00ffff0100000000, 0x00ffff0100000101,
+    0x00ffff01000100ff, 0x00ffff0100010100, 0x00ffff0101ff0100, 0x00ffff01010000ff,
+    0x00ffff0101010000, 0x00ff00ffffffff00, 0x00ff00ffff000000, 0x00ff00ffff000100,
+    0x00ff00ffff010100, 0x00ff00ff00ff0000, 0x00ff00ff00ff01ff, 0x00ff00ff00ff0101,
+    0x00ff00ff0000ff00, 0x00ff00ff000000ff, 0x00ff00ff00000000, 0x00ff00ff00000001,
+    0x00ff00ff0001ff00, 0x00ff00ff0001ff01, 0x00ff00ff00010000, 0x00ff00ff000101ff,
+    0x00ff00ff00010101, 0x00ff00ff01ffff00, 0x00ff00ff01ff0001, 0x00ff00ff01ff0100,
+    0x00ff00ff0100ffff, 0x00ff00ff0100ff01, 0x00ff00ff01000000, 0x00ff00ff0101ffff,
+    0x00ff00ff0101ff00, 0x00ff00ff01010100, 0x00ff0000ffffff00, 0x00ff0000ffffff01,
+    0x00ff0000ffff0000, 0x00ff0000ffff0101, 0x00ff0000ff00ff00, 0x00ff0000ff0000ff,
+    0x00ff0000ff000000, 0x00ff0000ff000001, 0x00ff0000ff000100, 0x00ff0000ff01ffff,
+    0x00ff0000ff010000, 0x00ff0000ff010101, 0x00ff000000ffff00, 0x00ff000000ff00ff,
+    0x00ff000000ff0000, 0x00ff000000ff0001, 0x00ff000000ff0100, 0x00ff00000000ffff,
+    0x00ff00000000ff00, 0x00ff0000000000ff, 0x00ff000000000000, 0x00ff000000000001,
+    0x00ff0000000001ff, 0x00ff000000000100, 0x00ff00000001ff00, 0x00ff0000000100ff,
+    0x00ff000000010000, 0x00ff000000010001, 0x00ff000000010100, 0x00ff000001ffff01,
+    0x00ff000001ff00ff, 0x00ff000001ff0000, 0x00ff000001ff01ff, 0x00ff00000100ff00,
+    0x00ff0000010000ff, 0x00ff000001000000, 0x00ff000001000001, 0x00ff000001000100,
+    0x00ff000001000101, 0x00ff000001010000, 0x00ff0000010101ff, 0x00ff000001010101,
+    0x00ff0001ffffff00, 0x00ff0001ffff0000, 0x00ff0001ffff0100, 0x00ff0001ff0000ff,
+    0x00ff0001ff000000, 0x00ff0001ff0001ff, 0x00ff0001ff000101, 0x00ff0001ff01ff00,
+    0x00ff0001ff0100ff, 0x00ff0001ff010100, 0x00ff000100ffffff, 0x00ff000100ffff01,
+    0x00ff000100ff0000, 0x00ff000100ff01ff, 0x00ff00010000ffff, 0x00ff00010000ff00,
+    0x00ff00010000ff01, 0x00ff000100000000, 0x00ff000100000001, 0x00ff000100000100,
+    0x00ff00010001ff01, 0x00ff000100010000, 0x00ff0001000101ff, 0x00ff000101ffff00,
+    0x00ff000101ff0000, 0x00ff000101ff0101, 0x00ff0001010000ff, 0x00ff000101000000,
+    0x00ff00010101ff00, 0x00ff0001010100ff, 0x00ff000101010001, 0x00ff01ffffff0000,
+    0x00ff01ffff00ff00, 0x00ff01ffff000000, 0x00ff01ffff000101, 0x00ff01ffff010000,
+    0x00ff01ff00ffff01, 0x00ff01ff00ff0100, 0x00ff01ff0000ffff, 0x00ff01ff00000000,
+    0x00ff01ff000001ff, 0x00ff01ff0001ff00, 0x00ff01ff000100ff, 0x00ff01ff00010001,
+    0x00ff01ff00010100, 0x00ff01ff01ff0000, 0x00ff01ff0100ff00, 0x00ff01ff010000ff,
+    0x00ff01ff01000001, 0x00ff01ff01000100, 0x00ff01ff01010000, 0x00ff0100ffffff00,
+    0x00ff0100ffff0000, 0x00ff0100ffff0001, 0x00ff0100ffff0101, 0x00ff0100ff00ffff,
+    0x00ff0100ff0000ff, 0x00ff0100ff000000, 0x00ff0100ff0001ff, 0x00ff0100ff01ff00,
+    0x00ff0100ff0100ff, 0x00ff0100ff010001, 0x00ff010000ffffff, 0x00ff010000ff0000,
+    0x00ff010000ff0101, 0x00ff01000000ff00, 0x00ff01000000ff01, 0x00ff0100000000ff,
+    0x00ff010000000000, 0x00ff010000000001, 0x00ff010000000100, 0x00ff01000001ffff,
+    0x00ff01000001ff01, 0x00ff010000010000, 0x00ff010000010001, 0x00ff010000010101,
+    0x00ff010001ff0001, 0x00ff010001ff0100, 0x00ff01000100ff01, 0x00ff010001000000,
+    0x00ff010001000001, 0x00ff0100010001ff, 0x00ff01000101ff00, 0x00ff0100010100ff,
+    0x00ff010001010001, 0x00ff010001010100, 0x00ff0101ff000001, 0x00ff010100ff00ff,
+    0x00ff010100ff0001, 0x00ff010100ff0100, 0x00ff010100000000, 0x00ff0101000001ff,
+    0x00ff010100000101, 0x00ff0101000100ff, 0x00ff010100010100, 0x00ff0101010000ff,
+    0x00ff010101010000, 0x0000ffffffffff00, 0x0000ffffffff00ff, 0x0000ffffffff0000,
+    0x0000ffffffff0001, 0x0000ffffffff0100, 0x0000ffffff00ff01, 0x0000ffffff000000,
+    0x0000ffffff000101, 0x0000ffffff01ff00, 0x0000ffffff0100ff, 0x0000ffffff010100,
+    0x0000ffff00ffffff, 0x0000ffff00ff0000, 0x0000ffff00ff01ff, 0x0000ffff0000ff00,
+    0x0000ffff000000ff, 0x0000ffff00000000, 0x0000ffff00000001, 0x0000ffff00000100,
+    0x0000ffff00010000, 0x0000ffff000101ff, 0x0000ffff01ff0001, 0x0000ffff01ff0100,
+    0x0000ffff01000000, 0x0000ffff010001ff, 0x0000ffff0101ffff, 0x0000ffff0101ff00,
+    0x0000ffff01010001, 0x0000ffff01010100, 0x0000ff00ffff0000, 0x0000ff00ffff01ff,
+    0x0000ff00ffff0100, 0x0000ff00ffff0101, 0x0000ff00ff00ff00, 0x0000ff00ff0000ff,
+    0x0000ff00ff000000, 0x0000ff00ff000001, 0x0000ff00ff0001ff, 0x0000ff00ff000100,
+    0x0000ff00ff01ffff, 0x0000ff00ff010000, 0x0000ff00ff010001, 0x0000ff00ff0101ff,
+    0x0000ff00ff010101, 0x0000ff0000ffff00, 0x0000ff0000ff00ff, 0x0000ff0000ff0000,
+    0x0000ff0000ff0001, 0x0000ff0000ff0100, 0x0000ff000000ffff, 0x0000ff000000ff00,
+    0x0000ff000000ff01, 0x0000ff00000000ff, 0x0000ff0000000000, 0x0000ff0000000001,
+    0x0000ff00000001ff, 0x0000ff0000000100, 0x0000ff0000000101, 0x0000ff000001ff00,
+    0x0000ff00000100ff, 0x0000ff0000010000, 0x0000ff0000010001, 0x0000ff0000010100,
+    0x0000ff0001ffff01, 0x0000ff0001ff0000, 0x0000ff000100ff00, 0x0000ff00010000ff,
+    0x0000ff0001000000, 0x0000ff0001000001, 0x0000ff0001000100, 0x0000ff000101ffff,
+    0x0000ff0001010000, 0x0000ff0001010101, 0x0000ff01ffffff00, 0x0000ff01ffff0001,
+    0x0000ff01ff00ff01, 0x0000ff01ff000000, 0x0000ff01ff000101, 0x0000ff01ff01ff00,
+    0x0000ff01ff0100ff, 0x0000ff0100ffff01, 0x0000ff0100ff0000, 0x0000ff0100ff0101,
+    0x0000ff010000ff00, 0x0000ff01000000ff, 0x0000ff0100000000, 0x0000ff0100000001,
+    0x0000ff0100000100, 0x0000ff010001ff01, 0x0000ff0100010000, 0x0000ff0101ff0000,
+    0x0000ff010100ffff, 0x0000ff010100ff01, 0x0000ff0101000000, 0x0000ff0101000100,
+    0x0000ff0101000101, 0x0000ff01010100ff, 0x000000ffffff00ff, 0x000000ffffff0000,
+    0x000000ffff00ff00, 0x000000ffff0000ff, 0x000000ffff000000, 0x000000ffff000001,
+    0x000000ffff0001ff, 0x000000ffff000100, 0x000000ffff01ff00, 0x000000ffff010000,
+    0x000000ffff0101ff, 0x000000ffff010101, 0x000000ff00ffff00, 0x000000ff00ff00ff,
+    0x000000ff00ff0000, 0x000000ff00ff0001, 0x000000ff00ff0100, 0x000000ff00ff0101,
+    0x000000ff0000ffff, 0x000000ff0000ff00, 0x000000ff000000ff, 0x000000ff00000000,
+    0x000000ff00000001, 0x000000ff000001ff, 0x000000ff00000100, 0x000000ff00000101,
+    0x000000ff0001ff00, 0x000000ff0001ff01, 0x000000ff000100ff, 0x000000ff00010000,
+    0x000000ff00010001, 0x000000ff00010100, 0x000000ff01ffffff, 0x000000ff01ff01ff,
+    0x000000ff01ff0101, 0x000000ff0100ff00, 0x000000ff010000ff, 0x000000ff01000000,
+    0x000000ff01000001, 0x000000ff01000100, 0x000000ff0101ff00, 0x000000ff010100ff,
+    0x000000ff01010000, 0x000000ff01010101, 0x00000000ffffff00, 0x00000000ffffff01,
+    0x00000000ffff00ff, 0x00000000ffff0000, 0x00000000ffff0001, 0x00000000ffff0100,
+    0x00000000ff00ffff, 0x00000000ff00ff00, 0x00000000ff00ff01, 0x00000000ff0000ff,
+    0x00000000ff000000, 0x00000000ff000001, 0x00000000ff000100, 0x00000000ff000101,
+    0x00000000ff01ff00, 0x00000000ff0100ff, 0x00000000ff010000, 0x00000000ff010001,
+    0x00000000ff010100, 0x0000000000ffffff, 0x0000000000ffff00, 0x0000000000ffff01,
+    0x0000000000ff00ff, 0x0000000000ff0000, 0x0000000000ff0001, 0x0000000000ff01ff,
+    0x0000000000ff0100, 0x000000000000ffff, 0x000000000000ff00, 0x000000000000ff01,
+    0x00000000000000ff, 0x0000000000000000, 0x0000000000000001, 0x00000000000001ff,
+    0x0000000000000100, 0x0000000000000101, 0x000000000001ffff, 0x000000000001ff00,
+    0x00000000000100ff, 0x0000000000010000, 0x0000000000010001, 0x00000000000101ff,
+    0x0000000000010100, 0x0000000000010101, 0x0000000001ffff00, 0x0000000001ff00ff,
+    0x0000000001ff0000, 0x0000000001ff0100, 0x0000000001ff0101, 0x000000000100ffff,
+    0x000000000100ff00, 0x00000000010000ff, 0x0000000001000000, 0x0000000001000001,
+    0x00000000010001ff, 0x0000000001000100, 0x000000000101ff00, 0x00000000010100ff,
+    0x0000000001010000, 0x0000000001010001, 0x0000000001010100, 0x00000001ffffffff,
+    0x00000001ffffff00, 0x00000001ffffff01, 0x00000001ffff00ff, 0x00000001ffff0001,
+    0x00000001ffff01ff, 0x00000001ffff0100, 0x00000001ff00ff00, 0x00000001ff0000ff,
+    0x00000001ff000000, 0x00000001ff0001ff, 0x00000001ff000100, 0x00000001ff01ffff,
+    0x00000001ff01ff00, 0x00000001ff01ff01, 0x00000001ff0100ff, 0x00000001ff010000,
+    0x00000001ff010001, 0x00000001ff0101ff, 0x00000001ff010100, 0x0000000100ffff00,
+    0x0000000100ff0000, 0x0000000100ff0001, 0x0000000100ff01ff, 0x0000000100ff0100,
+    0x0000000100ff0101, 0x000000010000ffff, 0x000000010000ff00, 0x000000010000ff01,
+    0x00000001000000ff, 0x0000000100000000, 0x0000000100000001, 0x00000001000001ff,
+    0x0000000100000100, 0x0000000100000101, 0x000000010001ff00, 0x00000001000100ff,
+    0x0000000100010000, 0x0000000100010100, 0x0000000101ffff01, 0x0000000101ff0000,
+    0x0000000101ff0001, 0x0000000101ff01ff, 0x0000000101ff0100, 0x0000000101ff0101,
+    0x000000010100ff00, 0x0000000101000000, 0x0000000101000101, 0x000000010101ff01,
+    0x0000000101010000, 0x0000000101010001, 0x00000001010101ff, 0x0000000101010100,
+    0x000001ffffff00ff, 0x000001ffffff0000, 0x000001ffffff0001, 0x000001ffffff0100,
+    0x000001ffff00ffff, 0x000001ffff000000, 0x000001ffff0001ff, 0x000001ffff01ff00,
+    0x000001ffff010101, 0x000001ff00ff0000, 0x000001ff00ff01ff, 0x000001ff00ff0101,
+    0x000001ff0000ff00, 0x000001ff000000ff, 0x000001ff00000000, 0x000001ff00000001,
+    0x000001ff000001ff, 0x000001ff00000100, 0x000001ff0001ffff, 0x000001ff0001ff01,
+    0x000001ff000100ff, 0x000001ff00010000, 0x000001ff01ffff01, 0x000001ff01ff0100,
+    0x000001ff0100ffff, 0x000001ff0100ff01, 0x000001ff01000000, 0x000001ff010001ff,
+    0x000001ff0101ff00, 0x000001ff01010100, 0x00000100ffffff00, 0x00000100ffffff01,
+    0x00000100ffff0000, 0x00000100ffff0101, 0x00000100ff00ff00, 0x00000100ff0000ff,
+    0x00000100ff000000, 0x00000100ff000001, 0x00000100ff000100, 0x00000100ff010000,
+    0x0000010000ffff00, 0x0000010000ff00ff, 0x0000010000ff0000, 0x0000010000ff0001,
+    0x0000010000ff0100, 0x000001000000ffff, 0x000001000000ff00, 0x000001000000ff01,
+    0x00000100000000ff, 0x0000010000000000, 0x0000010000000001, 0x00000100000001ff,
+    0x0000010000000100, 0x0000010000000101, 0x000001000001ff00, 0x00000100000100ff,
+    0x0000010000010000, 0x0000010000010001, 0x0000010000010100, 0x0000010001ffff00,
+    0x0000010001ff0000, 0x0000010001ff0100, 0x000001000100ff00, 0x00000100010000ff,
+    0x0000010001000000, 0x0000010001000001, 0x00000100010001ff, 0x0000010001000100,
+    0x0000010001010000, 0x00000101ffff00ff, 0x00000101ffff01ff, 0x00000101ff000000,
+    0x00000101ff000101, 0x00000101ff01ffff, 0x00000101ff010000, 0x00000101ff010001,
+    0x00000101ff010100, 0x0000010100ff0000, 0x0000010100ff01ff, 0x0000010100ff0100,
+    0x000001010000ff00, 0x0000010100000000, 0x0000010100000001, 0x00000101000001ff,
+    0x0000010100000100, 0x000001010001ff01, 0x0000010100010000, 0x00000101000101ff,
+    0x0000010100010101, 0x0000010101ffff00, 0x0000010101ff0101, 0x000001010100ff01,
+    0x0000010101000000, 0x0000010101000001, 0x00000101010001ff, 0x0000010101000101,
+    0x000001010101ff00, 0x0001ffffffff0000, 0x0001ffffff0000ff, 0x0001ffffff000001,
+    0x0001ffffff000100, 0x0001ffffff010000, 0x0001ffff00ff00ff, 0x0001ffff0000ffff,
+    0x0001ffff00000000, 0x0001ffff00000001, 0x0001ffff000001ff, 0x0001ffff00000101,
+    0x0001ffff0001ff00, 0x0001ffff000100ff, 0x0001ffff00010001, 0x0001ffff00010100,
+    0x0001ffff01ffff00, 0x0001ffff01000001, 0x0001ffff01010000, 0x0001ff00ffffff00,
+    0x0001ff00ffff00ff, 0x0001ff00ffff0001, 0x0001ff00ffff0100, 0x0001ff00ff00ff01,
+    0x0001ff00ff000000, 0x0001ff00ff01ff00, 0x0001ff00ff01ff01, 0x0001ff00ff010001,
+    0x0001ff00ff010100, 0x0001ff0000ff0000, 0x0001ff0000ff0100, 0x0001ff000000ff00,
+    0x0001ff0000000000, 0x0001ff0000000001, 0x0001ff0000000100, 0x0001ff0000010000,
+    0x0001ff0000010001, 0x0001ff0000010101, 0x0001ff0001ff00ff, 0x0001ff0001ff0101,
+    0x0001ff000100ff01, 0x0001ff0001000000, 0x0001ff000101ff00, 0x0001ff0001010001,
+    0x0001ff0001010100, 0x0001ff01ff00ff00, 0x0001ff01ff000001, 0x0001ff01ff000100,
+    0x0001ff0100ffffff, 0x0001ff0100ffff00, 0x0001ff0100ff0001, 0x0001ff0100000000,
+    0x0001ff0100000001, 0x0001ff01000001ff, 0x0001ff010001ffff, 0x0001ff0101ff0000,
+    0x0001ff010100ff00, 0x0001ff0101000001, 0x0001ff0101010000, 0x000100ffff00ff00,
+    0x000100ffff00ff01, 0x000100ffff000000, 0x000100ffff000001, 0x000100ffff000101,
+    0x000100ffff01ff00, 0x000100ffff010001, 0x000100ffff010100, 0x000100ff00ffffff,
+    0x000100ff00ffff01, 0x000100ff00ff0000, 0x000100ff00ff01ff, 0x000100ff00ff0101,
+    0x000100ff0000ff00, 0x000100ff000000ff, 0x000100ff00000000, 0x000100ff00000001,
+    0x000100ff00000100, 0x000100ff00000101, 0x000100ff0001ffff, 0x000100ff0001ff01,
+    0x000100ff00010000, 0x000100ff01ff00ff, 0x000100ff01ff0000, 0x000100ff01ff0100,
+    0x000100ff0100ffff, 0x000100ff0100ff01, 0x000100ff010000ff, 0x000100ff01000000,
+    0x000100ff01000001, 0x000100ff010001ff, 0x000100ff01000101, 0x000100ff0101ff00,
+    0x000100ff010100ff, 0x000100ff01010100, 0x00010000ffff0000, 0x00010000ffff01ff,
+    0x00010000ffff0101, 0x00010000ff00ff00, 0x00010000ff000000, 0x00010000ff000001,
+    0x00010000ff000100, 0x0001000000ff00ff, 0x0001000000ff0000, 0x0001000000ff0001,
+    0x0001000000ff0100, 0x000100000000ffff, 0x000100000000ff00, 0x00010000000000ff,
+    0x0001000000000000, 0x0001000000000001, 0x0001000000000100, 0x000100000001ff00,
+    0x00010000000100ff, 0x0001000000010000, 0x0001000000010001, 0x0001000000010100,
+    0x0001000001ff0001, 0x0001000001ff0100, 0x0001000001ff0101, 0x000100000100ff00,
+    0x0001000001000000, 0x0001000001000001, 0x0001000001000100, 0x0001000001000101,
+    0x000100000101ff01, 0x0001000001010000, 0x0001000001010001, 0x00010000010101ff,
+    0x00010001ffffff01, 0x00010001ffff0100, 0x00010001ff000000, 0x00010001ff01ffff,
+    0x00010001ff010001, 0x00010001ff0101ff, 0x00010001ff010100, 0x0001000100ffffff,
+    0x0001000100ff0000, 0x0001000100ff01ff, 0x0001000100ff0101, 0x000100010000ff00,
+    0x00010001000000ff, 0x0001000100000000, 0x0001000100000001, 0x00010001000001ff,
+    0x0001000100000101, 0x000100010001ffff, 0x0001000100010000, 0x00010001000101ff,
+    0x0001000101ffffff, 0x0001000101ffff01, 0x0001000101ff0000, 0x0001000101ff0101,
+    0x00010001010000ff, 0x0001000101000001, 0x00010001010001ff, 0x0001000101000100,
+    0x000100010101ffff, 0x00010001010100ff, 0x0001000101010001, 0x0001000101010101,
+    0x000101ffff000001, 0x000101ffff000100, 0x000101ffff010000, 0x000101ff00ffff00,
+    0x000101ff0000ff01, 0x000101ff00000000, 0x000101ff00000101, 0x000101ff0001ff00,
+    0x000101ff00010100, 0x000101ff01ff0000, 0x000101ff0100ff00, 0x000101ff010001ff,
+    0x000101ff01010001, 0x00010100ffffff00, 0x00010100ffff00ff, 0x00010100ff00ffff,
+    0x00010100ff000000, 0x00010100ff01ff00, 0x00010100ff0100ff, 0x00010100ff010001,
+    0x00010100ff010100, 0x0001010000ffffff, 0x0001010000ffff00, 0x0001010000ff0000,
+    0x0001010000ff0001, 0x0001010000ff01ff, 0x000101000000ff00, 0x00010100000000ff,
+    0x0001010000000000, 0x0001010000000001, 0x0001010000000100, 0x000101000001ffff,
+    0x0001010000010000, 0x0001010000010101, 0x0001010001ffff01, 0x0001010001ff00ff,
+    0x0001010001ff0101, 0x0001010001000000, 0x000101000101ff00, 0x00010100010100ff,
+    0x0001010001010000, 0x0001010001010100, 0x00010101ff00ff00, 0x00010101ff000001,
+    0x00010101ff0001ff, 0x0001010100ffff00, 0x0001010100ff00ff, 0x0001010100ff0100,
+    0x000101010000ffff, 0x0001010100000000, 0x00010101000001ff, 0x0001010100000101,
+    0x00010101000100ff, 0x0001010100010000, 0x0001010100010100, 0x0001010101ff0001,
+    0x00010101010000ff, 0x00010101010001ff, 0x0001010101000101, 0x0001010101010001,
+    0x01ffffffffffffff, 0x01ffffffffffff01, 0x01ffffffffff01ff, 0x01ffffffffff0101,
+    0x01ffffffff01ffff, 0x01ffffffff01ff01, 0x01ffffffff0101ff, 0x01ffffffff010101,
+    0x01ffffff00ff0000, 0x01ffffff0000ffff, 0x01ffffff0000ff00, 0x01ffffff000000ff,
+    0x01ffffff00000001, 0x01ffffff00000100, 0x01ffffff00010000, 0x01ffffff01ffffff,
+    0x01ffffff01ffff01, 0x01ffffff01ff01ff, 0x01ffffff01ff0101, 0x01ffffff01000000,
+    0x01ffffff0101ffff, 0x01ffffff0101ff01, 0x01ffffff010101ff, 0x01ffffff01010101,
+    0x01ffff00ffff0000, 0x01ffff00ff00ff00, 0x01ffff00ff0000ff, 0x01ffff00ff000001,
+    0x01ffff00ff000100, 0x01ffff00ff010000, 0x01ffff0000ffff00, 0x01ffff0000ff00ff,
+    0x01ffff0000ff0100, 0x01ffff000000ffff, 0x01ffff000000ff01, 0x01ffff0000000000,
+    0x01ffff0000000001, 0x01ffff00000001ff, 0x01ffff0000000100, 0x01ffff00000100ff,
+    0x01ffff0000010001, 0x01ffff0000010100, 0x01ffff0001ff0000, 0x01ffff0001ff0100,
+    0x01ffff00010000ff, 0x01ffff0001000001, 0x01ffff0001000100, 0x01ffff0001010000,
+    0x01ffff01ffffffff, 0x01ffff01ffffff01, 0x01ffff01ffff01ff, 0x01ffff01ffff0101,
+    0x01ffff01ff000000, 0x01ffff01ff01ffff, 0x01ffff01ff01ff01, 0x01ffff01ff0101ff,
+    0x01ffff01ff010101, 0x01ffff010000ff00, 0x01ffff01000000ff, 0x01ffff0100000100,
+    0x01ffff0100010000, 0x01ffff0101ffffff, 0x01ffff0101ffff01, 0x01ffff0101ff01ff,
+    0x01ffff0101ff0101, 0x01ffff0101000000, 0x01ffff010101ffff, 0x01ffff010101ff01,
+    0x01ffff01010101ff, 0x01ffff0101010101, 0x01ff00ffff0000ff, 0x01ff00ffff000100,
+    0x01ff00ff00ffff00, 0x01ff00ff00ff00ff, 0x01ff00ff0000ff00, 0x01ff00ff00000000,
+    0x01ff00ff00000101, 0x01ff00ff0001ff00, 0x01ff00ff000100ff, 0x01ff00ff00010100,
+    0x01ff00ff010000ff, 0x01ff00ff01000100, 0x01ff0000ffffff00, 0x01ff0000ffff0100,
+    0x01ff0000ff00ff01, 0x01ff0000ff000000, 0x01ff0000ff000101, 0x01ff0000ff010001,
+    0x01ff0000ff010100, 0x01ff000000ffffff, 0x01ff000000ffff00, 0x01ff000000ff0000,
+    0x01ff000000ff01ff, 0x01ff00000000ff00, 0x01ff0000000000ff, 0x01ff000000000000,
+    0x01ff000000000001, 0x01ff000000000100, 0x01ff000000000101, 0x01ff000000010000,
+    0x01ff000000010001, 0x01ff0000000101ff, 0x01ff000000010101, 0x01ff000001ffff00,
+    0x01ff000001ff00ff, 0x01ff000001ff0001, 0x01ff000001ff0100, 0x01ff00000100ffff,
+    0x01ff00000100ff01, 0x01ff000001000000, 0x01ff0000010001ff, 0x01ff000001010001,
+    0x01ff0001ff00ff00, 0x01ff0001ff000001, 0x01ff0001ff000100, 0x01ff0001ff010000,
+    0x01ff000100ffff00, 0x01ff000100ff00ff, 0x01ff000100ff0100, 0x01ff000100ff0101,
+    0x01ff00010000ffff, 0x01ff000100000000, 0x01ff000100000100, 0x01ff000100000101,
+    0x01ff00010001ff00, 0x01ff000100010001, 0x01ff000100010101, 0x01ff000101ff0000,
+    0x01ff00010100ff00, 0x01ff000101000101, 0x01ff0001010100ff, 0x01ff01ffffffffff,
+    0x01ff01ffffffff01, 0x01ff01ffffff01ff, 0x01ff01ffffff0101, 0x01ff01ffff000000,
+    0x01ff01ffff01ffff, 0x01ff01ffff01ff01, 0x01ff01ffff0101ff, 0x01ff01ffff010101,
+    0x01ff01ff00ffff00, 0x01ff01ff00ff0000, 0x01ff01ff0000ff00, 0x01ff01ff000000ff,
+    0x01ff01ff00000100, 0x01ff01ff00010000, 0x01ff01ff00010100, 0x01ff01ff01ffffff,
+    0x01ff01ff01ffff01, 0x01ff01ff01ff01ff, 0x01ff01ff01ff0101, 0x01ff01ff01000000,
+    0x01ff01ff0101ffff, 0x01ff01ff0101ff01, 0x01ff01ff010101ff, 0x01ff01ff01010101,
+    0x01ff0100ffff0000, 0x01ff0100ffff0001, 0x01ff0100ff00ff00, 0x01ff0100ff0000ff,
+    0x01ff0100ff000001, 0x01ff0100ff010000, 0x01ff010000ffff00, 0x01ff010000ff00ff,
+    0x01ff010000ff0001, 0x01ff010000ff0100, 0x01ff01000000ffff, 0x01ff01000000ff01,
+    0x01ff010000000000, 0x01ff010000000101, 0x01ff01000001ff00, 0x01ff0100000100ff,
+    0x01ff010001ff0000, 0x01ff010001000001, 0x01ff010001000100, 0x01ff010001010000,
+    0x01ff0101ffffffff, 0x01ff0101ffffff01, 0x01ff0101ffff01ff, 0x01ff0101ffff0101,
+    0x01ff0101ff000000, 0x01ff0101ff01ffff, 0x01ff0101ff01ff01, 0x01ff0101ff0101ff,
+    0x01ff0101ff010101, 0x01ff010100ff0000, 0x01ff01010000ff00, 0x01ff0101000000ff,
+    0x01ff010100000001, 0x01ff010101ffffff, 0x01ff010101ffff01, 0x01ff010101ff01ff,
+    0x01ff010101ff0101, 0x01ff010101000000, 0x01ff01010101ffff, 0x01ff01010101ff01,
+    0x01ff0101010101ff, 0x01ff010101010101, 0x0100ffffffff0000, 0x0100ffffff00ff00,
+    0x0100ffffff000001, 0x0100ffffff0001ff, 0x0100ffffff000100, 0x0100ffffff010000,
+    0x0100ffff00ffff00, 0x0100ffff00ff0001, 0x0100ffff00ff0100, 0x0100ffff00000000,
+    0x0100ffff000001ff, 0x0100ffff00000101, 0x0100ffff00010100, 0x0100ffff00010101,
+    0x0100ffff01ff0000, 0x0100ffff0100ff00, 0x0100ffff010000ff, 0x0100ffff01000001,
+    0x0100ffff01000100, 0x0100ffff01010000, 0x0100ff00ffffff00, 0x0100ff00ffff00ff,
+    0x0100ff00ffff0001, 0x0100ff00ffff0100, 0x0100ff00ff00ffff, 0x0100ff00ff000000,
+    0x0100ff00ff0001ff, 0x0100ff00ff000101, 0x0100ff00ff01ff00, 0x0100ff00ff0100ff,
+    0x0100ff00ff010001, 0x0100ff00ff010100, 0x0100ff0000ffffff, 0x0100ff0000ff0000,
+    0x0100ff000000ffff, 0x0100ff000000ff00, 0x0100ff00000000ff, 0x0100ff0000000000,
+    0x0100ff0000000001, 0x0100ff0000000100, 0x0100ff000001ff01, 0x0100ff0000010000,
+    0x0100ff0001ff00ff, 0x0100ff0001ff0001, 0x0100ff000100ff01, 0x0100ff0001000000,
+    0x0100ff00010001ff, 0x0100ff000101ff00, 0x0100ff00010100ff, 0x0100ff0001010001,
+    0x0100ff0001010100, 0x0100ff01ffff0000, 0x0100ff01ff00ff00, 0x0100ff01ff0000ff,
+    0x0100ff01ff000100, 0x0100ff01ff010000, 0x0100ff0100ff00ff, 0x0100ff0100ff0001,
+    0x0100ff0100ff0100, 0x0100ff010000ffff, 0x0100ff010000ff01, 0x0100ff0100000000,
+    0x0100ff01000001ff, 0x0100ff0100010001, 0x0100ff0100010100, 0x0100ff0101ff0000,
+    0x0100ff01010000ff, 0x0100ff0101000001, 0x0100ff0101010100, 0x010000ffffffff00,
+    0x010000ffffff00ff, 0x010000ffffff0001, 0x010000ffff00ffff, 0x010000ffff000000,
+    0x010000ffff0001ff, 0x010000ffff010001, 0x010000ff00ffffff, 0x010000ff00ff0101,
+    0x010000ff0000ff00, 0x010000ff000000ff, 0x010000ff00000000, 0x010000ff00000001,
+    0x010000ff000001ff, 0x010000ff00000100, 0x010000ff0001ffff, 0x010000ff0001ff00,
+    0x010000ff0001ff01, 0x010000ff00010000, 0x010000ff01ff00ff, 0x010000ff01ff0001,
+    0x010000ff0100ff01, 0x010000ff010000ff, 0x010000ff01000000, 0x010000ff010001ff,
+    0x010000ff0101ff00, 0x010000ff01010100, 0x01000000ffffffff, 0x01000000ffff0000,
+    0x01000000ffff01ff, 0x01000000ffff0101, 0x01000000ff00ffff, 0x01000000ff00ff00,
+    0x01000000ff0000ff, 0x01000000ff000000, 0x01000000ff000001, 0x01000000ff000100,
+    0x01000000ff01ff00, 0x01000000ff010000, 0x01000000ff010100, 0x01000000ff010101,
+    0x0100000000ffff00, 0x0100000000ff00ff, 0x0100000000ff0000, 0x0100000000ff0001,
+    0x0100000000ff0100, 0x010000000000ffff, 0x010000000000ff00, 0x010000000000ff01,
+    0x01000000000000ff, 0x0100000000000000, 0x0100000000000001, 0x01000000000001ff,
+    0x0100000000000100, 0x0100000000000101, 0x010000000001ff00, 0x01000000000100ff,
+    0x0100000000010000, 0x0100000000010001, 0x0100000000010100, 0x0100000001ffff00,
+    0x0100000001ff0000, 0x0100000001ff01ff, 0x010000000100ff00, 0x010000000100ff01,
+    0x01000000010000ff, 0x0100000001000000, 0x0100000001000001, 0x0100000001000100,
+    0x0100000001000101, 0x010000000101ffff, 0x010000000101ff01, 0x0100000001010000,
+    0x01000000010101ff, 0x0100000001010101, 0x01000001ffffff00, 0x01000001ffff00ff,
+    0x01000001ff00ffff, 0x01000001ff000000, 0x01000001ff000100, 0x01000001ff01ffff,
+    0x01000001ff010001, 0x01000001ff010100, 0x0100000100ff0000, 0x0100000100ff01ff,
+    0x0100000100ff0100, 0x010000010000ff00, 0x010000010000ff01, 0x0100000100000000,
+    0x0100000100000001, 0x0100000100000100, 0x0100000100010000, 0x01000001000101ff,
+    0x0100000101ffff01, 0x0100000101ff00ff, 0x0100000101ff0100, 0x0100000101ff0101,
+    0x010000010100ff01, 0x01000001010000ff, 0x0100000101000000, 0x01000001010100ff,
+    0x0100000101010001, 0x0100000101010100, 0x010001ffffff0000, 0x010001ffff000001,
+    0x010001ffff000100, 0x010001ffff010000, 0x010001ff00ffff00, 0x010001ff00ff0001,
+    0x010001ff0000ffff, 0x010001ff0000ff01, 0x010001ff00000000, 0x010001ff00000001,
+    0x010001ff00000101, 0x010001ff000100ff, 0x010001ff00010000, 0x010001ff01ff0000,
+    0x010001ff0100ff00, 0x010001ff01000001, 0x010001ff01000100, 0x010001ff01010000,
+    0x01000100ffff00ff, 0x01000100ffff0001, 0x01000100ffff0100, 0x01000100ff00ffff,
+    0x01000100ff00ff01, 0x01000100ff000000, 0x01000100ff0001ff, 0x01000100ff000101,
+    0x01000100ff01ffff, 0x01000100ff01ff00, 0x01000100ff0100ff, 0x01000100ff010001,
+    0x0100010000ffffff, 0x0100010000ffff01, 0x0100010000ff0000, 0x0100010000ff01ff,
+    0x0100010000ff0101, 0x010001000000ff00, 0x01000100000000ff, 0x0100010000000000,
+    0x0100010000000001, 0x0100010000000100, 0x010001000001ff01, 0x0100010000010000,
+    0x0100010000010001, 0x0100010000010101, 0x0100010001ffff00, 0x0100010001ff00ff,
+    0x010001000100ffff, 0x010001000100ff01, 0x0100010001000000, 0x0100010001000101,
+    0x010001000101ff00, 0x0100010001010001, 0x01000101ffff0000, 0x01000101ff000000,
+    0x01000101ff010000, 0x0100010100ff00ff, 0x0100010100ff0001, 0x0100010100ff0100,
+    0x010001010000ffff, 0x0100010100000000, 0x01000101000001ff, 0x010001010001ff00,
+    0x0100010101ff0000, 0x010001010100ff00, 0x01000101010000ff, 0x0100010101000000,
+    0x0100010101000001, 0x0101ffffffffffff, 0x0101ffffffffff01, 0x0101ffffffff01ff,
+    0x0101ffffffff0101, 0x0101ffffff000000, 0x0101ffffff01ffff, 0x0101ffffff01ff01,
+    0x0101ffffff0101ff, 0x0101ffffff010101, 0x0101ffff00ff0000, 0x0101ffff0000ff00,
+    0x0101ffff000000ff, 0x0101ffff00000001, 0x0101ffff00000100, 0x0101ffff01ffffff,
+    0x0101ffff01ffff01, 0x0101ffff01ff01ff, 0x0101ffff01ff0101, 0x0101ffff01000000,
+    0x0101ffff0101ffff, 0x0101ffff0101ff01, 0x0101ffff010101ff, 0x0101ffff01010101,
+    0x0101ff00ffff0000, 0x0101ff00ffff0100, 0x0101ff00ff00ff00, 0x0101ff00ff0000ff,
+    0x0101ff00ff000001, 0x0101ff00ff000100, 0x0101ff00ff000101, 0x0101ff0000ff0001,
+    0x0101ff0000ff0100, 0x0101ff000000ff00, 0x0101ff0000000000, 0x0101ff00000001ff,
+    0x0101ff0000000101, 0x0101ff000001ff00, 0x0101ff00000100ff, 0x0101ff0001ff0000,
+    0x0101ff000100ffff, 0x0101ff000100ff01, 0x0101ff0001000001, 0x0101ff0001000100,
+    0x0101ff01ffffff01, 0x0101ff01ffff01ff, 0x0101ff01ffff0101, 0x0101ff01ff00ffff,
+    0x0101ff01ff000100, 0x0101ff01ff01ff01, 0x0101ff01ff0101ff, 0x0101ff01ff010101,
+    0x0101ff0100ff0000, 0x0101ff010000ff00, 0x0101ff0100000001, 0x0101ff0100000100,
+    0x0101ff0100010000, 0x0101ff0101ffffff, 0x0101ff0101ffff01, 0x0101ff0101ff01ff,
+    0x0101ff0101ff0101, 0x0101ff0101000000, 0x0101ff010101ffff, 0x0101ff010101ff01,
+    0x0101ff01010101ff, 0x0101ff0101010101, 0x010100ffff000100, 0x010100ffff010000,
+    0x010100ff00ffff00, 0x010100ff00ff00ff, 0x010100ff0000ffff, 0x010100ff000000ff,
+    0x010100ff00000000, 0x010100ff000001ff, 0x010100ff00000101, 0x010100ff0001ff00,
+    0x010100ff00010000, 0x010100ff00010001, 0x010100ff000101ff, 0x010100ff00010100,
+    0x010100ff01ff0000, 0x01010000ffff0001, 0x01010000ffff0100, 0x01010000ff00ffff,
+    0x01010000ff00ff01, 0x01010000ff000000, 0x01010000ff0001ff, 0x01010000ff010001,
+    0x01010000ff010100, 0x0101000000ffff01, 0x0101000000ff0000, 0x010100000000ff00,
+    0x01010000000000ff, 0x0101000000000000, 0x0101000000000001, 0x0101000000000100,
+    0x0101000000010000, 0x0101000000010101, 0x0101000001ffff00, 0x0101000001ff00ff,
+    0x0101000001ff0000, 0x0101000001ff0001, 0x0101000001ff0100, 0x010100000100ff01,
+    0x0101000001000000, 0x01010000010001ff, 0x01010001ffff0000, 0x01010001ff00ff00,
+    0x01010001ff000001, 0x01010001ff000101, 0x01010001ff01ff00, 0x01010001ff010000,
+    0x0101000100ff00ff, 0x0101000100ff0001, 0x0101000100ff0101, 0x010100010000ff01,
+    0x0101000100000000, 0x0101000100000001, 0x01010001000001ff, 0x010100010001ffff,
+    0x010100010001ff01, 0x0101000101ff0001, 0x010100010100ffff, 0x0101000101000000,
+    0x0101000101000001, 0x0101000101000100, 0x010100010101ff00, 0x01010001010100ff,
+    0x0101000101010001, 0x010101ffffffffff, 0x010101ffffffff01, 0x010101ffffff01ff,
+    0x010101ffffff0101, 0x010101ffff01ffff, 0x010101ffff01ff01, 0x010101ffff0101ff,
+    0x010101ffff010101, 0x010101ff0000ff00, 0x010101ff000000ff, 0x010101ff00000001,
+    0x010101ff00000100, 0x010101ff01ffffff, 0x010101ff01ffff01, 0x010101ff01ff01ff,
+    0x010101ff01ff0101, 0x010101ff01000000, 0x010101ff0101ffff, 0x010101ff0101ff01,
+    0x010101ff010101ff, 0x010101ff01010101, 0x01010100ffff0000, 0x01010100ff0000ff,
+    0x01010100ff000100, 0x01010100ff01ff00, 0x01010100ff010000, 0x0101010000ffff00,
+    0x010101000000ffff, 0x0101010000000000, 0x0101010000000101, 0x010101000001ff00,
+    0x0101010000010001, 0x0101010000010100, 0x010101000100ffff, 0x0101010001000001,
+    0x01010101ffffffff, 0x01010101ffffff01, 0x01010101ffff01ff, 0x01010101ffff0101,
+    0x01010101ff01ffff, 0x01010101ff01ff01, 0x01010101ff0101ff, 0x01010101ff010101,
+    0x010101010000ff00, 0x01010101000000ff, 0x0101010100000001, 0x0101010101ffffff,
+    0x0101010101ffff01, 0x0101010101ff01ff, 0x0101010101ff0101, 0x0101010101000000,
+    0x010101010101ffff, 0x010101010101ff01, 0x01010101010101ff, 0x0101010101010101,
+GGML_TABLE_END()
+#else
+GGML_TABLE_BEGIN(uint32_t, iq1s_grid_gpu, NGRID_IQ1S)
+    0x00000000, 0x00000002, 0x00000101, 0x00000200, 0x00000202, 0x00010001, 0x00010101, 0x00020000,
+    0x00020002, 0x00020200, 0x00020202, 0x01000101, 0x01010001, 0x01010100, 0x01010102, 0x01020101,
+    0x02000000, 0x02000002, 0x02000200, 0x02000202, 0x02010101, 0x02020000, 0x02020002, 0x02020200,
+    0x02020202, 0x00000110, 0x00000111, 0x00010011, 0x00010110, 0x00010112, 0x00010211, 0x00010212,
+    0x00020111, 0x01000011, 0x01000112, 0x01000211, 0x01010012, 0x01010111, 0x01010212, 0x01020011,
+    0x01020110, 0x01020112, 0x01020210, 0x02000111, 0x02010011, 0x02010110, 0x02010112, 0x02020111,
+    0x00000020, 0x00000022, 0x00000220, 0x00000222, 0x00010121, 0x00020020, 0x00020022, 0x00020220,
+    0x00020222, 0x01000121, 0x01010021, 0x01010221, 0x01020120, 0x01020221, 0x02000020, 0x02000022,
+    0x02000220, 0x02000222, 0x02010021, 0x02010121, 0x02010221, 0x02020020, 0x02020022, 0x02020220,
+    0x02020222, 0x00011001, 0x00011100, 0x00011102, 0x00021101, 0x01001001, 0x01001201, 0x01011101,
+    0x01011202, 0x01021100, 0x01021101, 0x02011001, 0x02011201, 0x02021101, 0x00001011, 0x00001110,
+    0x00001111, 0x00001112, 0x00011111, 0x00011210, 0x00011212, 0x00021211, 0x01001010, 0x01001111,
+    0x01001212, 0x01011010, 0x01011011, 0x01011110, 0x01011111, 0x01011112, 0x01011211, 0x01021010,
+    0x01021012, 0x01021111, 0x01021210, 0x01021212, 0x02001011, 0x02011011, 0x02011111, 0x02011210,
+    0x02011212, 0x02021011, 0x02021110, 0x02021111, 0x02021112, 0x02021211, 0x00011120, 0x00011221,
+    0x01001021, 0x01001120, 0x01011020, 0x01011022, 0x01011121, 0x01011220, 0x01021020, 0x01021021,
+    0x01021122, 0x01021221, 0x02001121, 0x02011021, 0x02011120, 0x02011221, 0x00002000, 0x00002002,
+    0x00002200, 0x00002202, 0x00012101, 0x00022000, 0x00022002, 0x00022200, 0x00022202, 0x01002101,
+    0x01012001, 0x01012102, 0x01022101, 0x02002000, 0x02002002, 0x02002200, 0x02002202, 0x02012101,
+    0x02022000, 0x02022002, 0x02022200, 0x02022202, 0x00002111, 0x00012011, 0x00012110, 0x00012211,
+    0x00022110, 0x00022111, 0x01002011, 0x01012010, 0x01012011, 0x01012111, 0x01022011, 0x01022110,
+    0x01022211, 0x02012011, 0x02012110, 0x02012112, 0x02012211, 0x02022111, 0x00002020, 0x00002022,
+    0x00002220, 0x00002222, 0x00012121, 0x00022020, 0x00022022, 0x00022220, 0x00022222, 0x01002121,
+    0x01012021, 0x01012221, 0x01022021, 0x01022121, 0x02002020, 0x02002022, 0x02002121, 0x02002220,
+    0x02002222, 0x02012121, 0x02022020, 0x02022022, 0x02022220, 0x02022222, 0x00110000, 0x00110001,
+    0x00110100, 0x00110201, 0x00120100, 0x00120101, 0x01100001, 0x01100100, 0x01110000, 0x01110101,
+    0x01110200, 0x01120001, 0x01120100, 0x01120101, 0x01120201, 0x02110001, 0x02110100, 0x02110102,
+    0x02120001, 0x02120101, 0x00100011, 0x00100110, 0x00100112, 0x00100211, 0x00110010, 0x00110012,
+    0x00110111, 0x00110210, 0x00120011, 0x00120110, 0x00120211, 0x01100111, 0x01100212, 0x01110010,
+    0x01110011, 0x01110012, 0x01110110, 0x01110111, 0x01110112, 0x01110211, 0x01120010, 0x01120111,
+    0x02100110, 0x02110012, 0x02110111, 0x02120011, 0x02120110, 0x00110021, 0x00110120, 0x00110122,
+    0x00120121, 0x01100020, 0x01100122, 0x01100221, 0x01110022, 0x01110121, 0x01110220, 0x01110222,
+    0x01120120, 0x01120122, 0x02100121, 0x02110021, 0x02110120, 0x02110122, 0x02120121, 0x00101001,
+    0x00101102, 0x00101201, 0x00111100, 0x00111101, 0x00111200, 0x00111201, 0x00121001, 0x00121102,
+    0x01101001, 0x01101101, 0x01101102, 0x01101200, 0x01101202, 0x01111001, 0x01111100, 0x01111101,
+    0x01111102, 0x01111201, 0x01121002, 0x01121101, 0x01121200, 0x02101100, 0x02101201, 0x02111000,
+    0x02111100, 0x02111101, 0x02111200, 0x02111201, 0x02111202, 0x02121001, 0x02121100, 0x02121101,
+    0x02121201, 0x00101012, 0x00101111, 0x00101212, 0x00111011, 0x00111110, 0x00111111, 0x00111112,
+    0x00111211, 0x00121010, 0x00121012, 0x00121111, 0x00121210, 0x00121212, 0x01101011, 0x01101110,
+    0x01101111, 0x01101112, 0x01111011, 0x01111012, 0x01111110, 0x01111111, 0x01111112, 0x01111211,
+    0x01111212, 0x01121011, 0x01121110, 0x01121111, 0x01121112, 0x01121211, 0x02101010, 0x02101012,
+    0x02101110, 0x02101111, 0x02101210, 0x02101212, 0x02111010, 0x02111011, 0x02111110, 0x02111111,
+    0x02111112, 0x02111211, 0x02111212, 0x02121010, 0x02121012, 0x02121111, 0x00101021, 0x00101120,
+    0x00101121, 0x00101122, 0x00111121, 0x00111122, 0x00111220, 0x00111222, 0x00121021, 0x00121122,
+    0x01101020, 0x01101022, 0x01101120, 0x01101121, 0x01101220, 0x01101222, 0x01111021, 0x01111121,
+    0x01111122, 0x01111220, 0x01111221, 0x01121021, 0x01121120, 0x01121121, 0x01121220, 0x01121221,
+    0x01121222, 0x02101122, 0x02101222, 0x02111022, 0x02111121, 0x02121120, 0x02121221, 0x00112001,
+    0x00112102, 0x00122101, 0x01102001, 0x01102100, 0x01102102, 0x01102201, 0x01112000, 0x01112101,
+    0x01112200, 0x01112202, 0x01122000, 0x01122001, 0x01122100, 0x01122102, 0x01122201, 0x02102101,
+    0x02112001, 0x02112100, 0x02122101, 0x00112010, 0x00112012, 0x00112111, 0x00112212, 0x00122011,
+    0x00122111, 0x01102012, 0x01102110, 0x01102111, 0x01102210, 0x01112011, 0x01112110, 0x01112111,
+    0x01112112, 0x01112211, 0x01112212, 0x01122010, 0x01122111, 0x01122212, 0x02102211, 0x02112011,
+    0x02112012, 0x02112111, 0x02112210, 0x02122011, 0x02122112, 0x02122211, 0x00102221, 0x00112122,
+    0x00122120, 0x00122122, 0x01102120, 0x01102122, 0x01102221, 0x01112020, 0x01112022, 0x01112121,
+    0x01112220, 0x01122021, 0x01122122, 0x01122221, 0x02102121, 0x02112021, 0x02112122, 0x02112222,
+    0x00200000, 0x00200002, 0x00200200, 0x00200202, 0x00210101, 0x00220000, 0x00220002, 0x00220101,
+    0x00220200, 0x00220202, 0x01200101, 0x01210001, 0x01210201, 0x01220001, 0x01220101, 0x02200000,
+    0x02200002, 0x02200200, 0x02200202, 0x02210101, 0x02220000, 0x02220002, 0x02220101, 0x02220200,
+    0x02220202, 0x00200111, 0x00210011, 0x00210110, 0x00210211, 0x00220111, 0x01200012, 0x01200110,
+    0x01200211, 0x01210111, 0x01210210, 0x01210212, 0x01220011, 0x01220110, 0x01220111, 0x01220112,
+    0x02200111, 0x02210010, 0x02210112, 0x02210211, 0x02220111, 0x00200021, 0x00200220, 0x00200222,
+    0x00210021, 0x00210121, 0x00220020, 0x00220022, 0x00220220, 0x00220222, 0x01200121, 0x01210021,
+    0x01210122, 0x01210221, 0x01220121, 0x02200021, 0x02200220, 0x02200222, 0x02210021, 0x02210121,
+    0x02220020, 0x02220022, 0x02220220, 0x02220222, 0x00201101, 0x00211100, 0x00211102, 0x00211201,
+    0x00221101, 0x01201100, 0x01201101, 0x01201102, 0x01201201, 0x01211002, 0x01211101, 0x01211200,
+    0x01211202, 0x01221102, 0x02201101, 0x02211001, 0x02211100, 0x02211201, 0x02221001, 0x02221101,
+    0x00201211, 0x00211111, 0x00221011, 0x00221211, 0x01201010, 0x01201111, 0x01201210, 0x01211011,
+    0x01211110, 0x01211111, 0x01211211, 0x01221012, 0x01221111, 0x01221210, 0x02201211, 0x02211010,
+    0x02211110, 0x02211111, 0x02211210, 0x02211212, 0x02221011, 0x02221110, 0x02221112, 0x02221211,
+    0x00201121, 0x00211020, 0x00211022, 0x00211221, 0x00221121, 0x01201021, 0x01201221, 0x01211121,
+    0x01221020, 0x01221021, 0x01221221, 0x02201120, 0x02201122, 0x02211020, 0x02211222, 0x00202000,
+    0x00202002, 0x00202200, 0x00202202, 0x00212101, 0x00222000, 0x00222002, 0x00222200, 0x00222202,
+    0x01202101, 0x01212001, 0x01212100, 0x01222101, 0x02202000, 0x02202002, 0x02202200, 0x02202202,
+    0x02222000, 0x02222002, 0x02222200, 0x02222202, 0x00202211, 0x00212011, 0x00212110, 0x00212211,
+    0x00222111, 0x01202112, 0x01202211, 0x01212012, 0x01212111, 0x01222011, 0x01222110, 0x01222112,
+    0x01222211, 0x02202111, 0x02212010, 0x02212112, 0x02212211, 0x02222110, 0x02222111, 0x00202020,
+    0x00202022, 0x00202220, 0x00202222, 0x00222020, 0x00222022, 0x00222220, 0x00222222, 0x01202121,
+    0x01212021, 0x01212122, 0x01212221, 0x01222121, 0x02202020, 0x02202022, 0x02202220, 0x02202222,
+    0x02212121, 0x02222020, 0x02222022, 0x02222220, 0x02222222, 0x10000101, 0x10010001, 0x10010102,
+    0x10020101, 0x11000201, 0x11010002, 0x11010101, 0x11010200, 0x11010202, 0x11020001, 0x11020100,
+    0x11020102, 0x12010100, 0x12010201, 0x12020001, 0x12020102, 0x10000010, 0x10000011, 0x10000110,
+    0x10000112, 0x10000211, 0x10010012, 0x10010111, 0x10010112, 0x10010210, 0x10010212, 0x10020011,
+    0x10020112, 0x10020211, 0x11000111, 0x11000210, 0x11000212, 0x11010011, 0x11010110, 0x11010111,
+    0x11010112, 0x11010211, 0x11010212, 0x11020111, 0x11020210, 0x11020212, 0x12000011, 0x12000110,
+    0x12000112, 0x12010010, 0x12010012, 0x12010111, 0x12020010, 0x12020011, 0x12020012, 0x10000121,
+    0x10010021, 0x10010120, 0x10010122, 0x10020121, 0x11000021, 0x11010022, 0x11010121, 0x11010222,
+    0x11020120, 0x11020221, 0x12000221, 0x12010120, 0x12020121, 0x10001001, 0x10011101, 0x10011201,
+    0x10021201, 0x11001101, 0x11001200, 0x11001202, 0x11011001, 0x11011100, 0x11011101, 0x11011102,
+    0x11021001, 0x11021002, 0x11021101, 0x11021200, 0x11021202, 0x12001001, 0x12001102, 0x12001201,
+    0x12011000, 0x12011002, 0x12011101, 0x12021000, 0x12021001, 0x12021201, 0x10001011, 0x10001012,
+    0x10001111, 0x10001212, 0x10011011, 0x10011110, 0x10011111, 0x10011112, 0x10011211, 0x10021010,
+    0x10021111, 0x10021212, 0x11001011, 0x11001110, 0x11001111, 0x11001112, 0x11001211, 0x11011010,
+    0x11011011, 0x11011110, 0x11011111, 0x11011112, 0x11011210, 0x11011211, 0x11021011, 0x11021110,
+    0x11021111, 0x11021112, 0x11021211, 0x12001012, 0x12001110, 0x12001111, 0x12001210, 0x12011011,
+    0x12011110, 0x12011111, 0x12011112, 0x12011211, 0x12011212, 0x12021111, 0x12021210, 0x12021212,
+    0x10001021, 0x10001121, 0x10001221, 0x10011120, 0x10011121, 0x10011220, 0x10011222, 0x10021021,
+    0x10021120, 0x10021221, 0x11001020, 0x11001022, 0x11001121, 0x11001220, 0x11011020, 0x11011021,
+    0x11011022, 0x11011121, 0x11011122, 0x11011221, 0x11021022, 0x11021121, 0x11021220, 0x12001021,
+    0x12001121, 0x12001222, 0x12011120, 0x12011121, 0x12021021, 0x12021120, 0x12021122, 0x10002101,
+    0x10012001, 0x10012101, 0x10012202, 0x10022101, 0x11002002, 0x11002201, 0x11012000, 0x11012101,
+    0x11012200, 0x11022001, 0x11022100, 0x11022102, 0x11022201, 0x12002101, 0x12012001, 0x12012100,
+    0x12012102, 0x12012201, 0x12022101, 0x10002011, 0x10002111, 0x10002112, 0x10002212, 0x10012010,
+    0x10012110, 0x10012111, 0x10012210, 0x10022011, 0x10022110, 0x10022112, 0x11002010, 0x11002111,
+    0x11002212, 0x11012011, 0x11012012, 0x11012110, 0x11012111, 0x11012112, 0x11012211, 0x11022010,
+    0x11022012, 0x11022111, 0x11022112, 0x11022212, 0x12002112, 0x12002211, 0x12012012, 0x12012111,
+    0x12012112, 0x12012210, 0x12022011, 0x12022110, 0x12022112, 0x12022211, 0x10012122, 0x11002120,
+    0x11002122, 0x11002221, 0x11012121, 0x11012220, 0x11012222, 0x11022120, 0x11022221, 0x12012120,
+    0x12022121, 0x10100001, 0x10100100, 0x10100101, 0x10100102, 0x10100201, 0x10110002, 0x10110101,
+    0x10110202, 0x10120001, 0x10120100, 0x10120201, 0x11100000, 0x11100101, 0x11100200, 0x11110001,
+    0x11110100, 0x11110101, 0x11110102, 0x11110201, 0x11120101, 0x11120200, 0x12100102, 0x12100201,
+    0x12110101, 0x12110200, 0x12120000, 0x12120001, 0x12120102, 0x12120201, 0x10100111, 0x10100210,
+    0x10100211, 0x10100212, 0x10110011, 0x10110110, 0x10110111, 0x10110112, 0x10110210, 0x10110211,
+    0x10120010, 0x10120111, 0x10120112, 0x10120210, 0x10120212, 0x11100011, 0x11100110, 0x11100111,
+    0x11100112, 0x11100211, 0x11110010, 0x11110011, 0x11110012, 0x11110110, 0x11110111, 0x11110112,
+    0x11110210, 0x11110211, 0x11110212, 0x11120011, 0x11120110, 0x11120111, 0x11120112, 0x11120211,
+    0x12100012, 0x12100111, 0x12110011, 0x12110110, 0x12110111, 0x12110112, 0x12110211, 0x12120010,
+    0x12120111, 0x12120212, 0x10100021, 0x10100122, 0x10110022, 0x10110121, 0x10110222, 0x10120021,
+    0x10120120, 0x11100022, 0x11100121, 0x11100222, 0x11110021, 0x11110120, 0x11110121, 0x11110122,
+    0x11110221, 0x11120022, 0x11120121, 0x12100121, 0x12110020, 0x12110022, 0x12110121, 0x12110221,
+    0x12110222, 0x12120120, 0x10101100, 0x10101101, 0x10111001, 0x10111100, 0x10111101, 0x10111102,
+    0x10111200, 0x10111201, 0x10121001, 0x10121101, 0x10121200, 0x10121202, 0x11101001, 0x11101100,
+    0x11101101, 0x11101102, 0x11101201, 0x11101202, 0x11111000, 0x11111001, 0x11111100, 0x11111101,
+    0x11111102, 0x11111200, 0x11111201, 0x11111202, 0x11121001, 0x11121002, 0x11121100, 0x11121101,
+    0x11121102, 0x11121201, 0x12101000, 0x12101200, 0x12101202, 0x12111001, 0x12111100, 0x12111101,
+    0x12111102, 0x12111201, 0x12121001, 0x12121100, 0x12121101, 0x12121202, 0x10101011, 0x10101012,
+    0x10101110, 0x10101111, 0x10101112, 0x10101211, 0x10111010, 0x10111011, 0x10111012, 0x10111110,
+    0x10111111, 0x10111112, 0x10111211, 0x10111212, 0x10121011, 0x10121110, 0x10121111, 0x10121112,
+    0x10121211, 0x11101010, 0x11101011, 0x11101012, 0x11101110, 0x11101111, 0x11101112, 0x11101210,
+    0x11101211, 0x11111010, 0x11111011, 0x11111012, 0x11111110, 0x11111111, 0x11111112, 0x11111210,
+    0x11111211, 0x11111212, 0x11121010, 0x11121011, 0x11121110, 0x11121111, 0x11121112, 0x11121210,
+    0x11121211, 0x11121212, 0x12101011, 0x12101110, 0x12101111, 0x12101211, 0x12101212, 0x12111010,
+    0x12111011, 0x12111110, 0x12111111, 0x12111112, 0x12111210, 0x12111211, 0x12121011, 0x12121110,
+    0x12121111, 0x12121112, 0x12121211, 0x10101020, 0x10101021, 0x10101022, 0x10101120, 0x10101122,
+    0x10101220, 0x10101221, 0x10111021, 0x10111120, 0x10111121, 0x10111220, 0x10111221, 0x10121020,
+    0x10121021, 0x10121022, 0x10121120, 0x10121121, 0x10121122, 0x10121220, 0x10121221, 0x11101021,
+    0x11101121, 0x11101122, 0x11101220, 0x11101221, 0x11101222, 0x11111020, 0x11111021, 0x11111022,
+    0x11111120, 0x11111121, 0x11111122, 0x11111220, 0x11111221, 0x11111222, 0x11121021, 0x11121120,
+    0x11121121, 0x11121221, 0x12101022, 0x12101121, 0x12101122, 0x12101220, 0x12101221, 0x12101222,
+    0x12111021, 0x12111121, 0x12111222, 0x12121022, 0x12121121, 0x12121122, 0x12121220, 0x12121221,
+    0x10102100, 0x10102101, 0x10102102, 0x10102201, 0x10112000, 0x10112101, 0x10112200, 0x10122001,
+    0x10122202, 0x11102101, 0x11102200, 0x11102202, 0x11112001, 0x11112100, 0x11112101, 0x11112102,
+    0x11112200, 0x11112201, 0x11122000, 0x11122002, 0x11122100, 0x11122101, 0x12102002, 0x12102201,
+    0x12112000, 0x12112002, 0x12112101, 0x12112200, 0x12122001, 0x12122201, 0x10102011, 0x10102012,
+    0x10102111, 0x10102212, 0x10112011, 0x10112110, 0x10112111, 0x10112112, 0x10112211, 0x10122111,
+    0x11102011, 0x11102110, 0x11102111, 0x11102112, 0x11102211, 0x11112010, 0x11112011, 0x11112012,
+    0x11112110, 0x11112111, 0x11112112, 0x11112210, 0x11112211, 0x11112212, 0x11122011, 0x11122110,
+    0x11122111, 0x11122112, 0x11122211, 0x12102011, 0x12102111, 0x12102211, 0x12112011, 0x12112110,
+    0x12112111, 0x12112112, 0x12112210, 0x12112211, 0x12122111, 0x10102120, 0x10102220, 0x10112121,
+    0x10112222, 0x10122020, 0x10122121, 0x10122122, 0x10122221, 0x11102121, 0x11102220, 0x11102221,
+    0x11112021, 0x11112121, 0x11112122, 0x11112220, 0x11112221, 0x11122022, 0x11122121, 0x11122220,
+    0x11122222, 0x12102021, 0x12102222, 0x12112022, 0x12112121, 0x12112122, 0x12112220, 0x12112222,
+    0x12122021, 0x10200101, 0x10210100, 0x10210102, 0x10210201, 0x10220101, 0x11200100, 0x11210000,
+    0x11210101, 0x11210102, 0x11210200, 0x11210202, 0x11220001, 0x11220100, 0x11220102, 0x11220201,
+    0x12200001, 0x12210102, 0x12220101, 0x10200011, 0x10200110, 0x10200112, 0x10200211, 0x10210012,
+    0x10210111, 0x10220011, 0x10220012, 0x10220112, 0x10220211, 0x11200111, 0x11200211, 0x11210011,
+    0x11210111, 0x11210112, 0x11210211, 0x11220111, 0x11220112, 0x11220212, 0x12200110, 0x12200212,
+    0x12210012, 0x12210111, 0x12220011, 0x12220112, 0x12220211, 0x10210021, 0x10210122, 0x10210221,
+    0x11200020, 0x11200021, 0x11200122, 0x11210121, 0x11210122, 0x11210220, 0x11220020, 0x12200121,
+    0x12210021, 0x12210122, 0x12220121, 0x10211001, 0x10211002, 0x10211101, 0x10211102, 0x10211202,
+    0x10221001, 0x10221102, 0x10221201, 0x11201000, 0x11201002, 0x11201101, 0x11201200, 0x11201202,
+    0x11211001, 0x11211100, 0x11211101, 0x11211102, 0x11211201, 0x11211202, 0x11221000, 0x11221002,
+    0x11221101, 0x12201100, 0x12201101, 0x12201201, 0x12211000, 0x12211002, 0x12211100, 0x12211101,
+    0x12211102, 0x12211200, 0x12211202, 0x12221001, 0x12221100, 0x12221201, 0x10201111, 0x10201210,
+    0x10201212, 0x10211011, 0x10211111, 0x10211112, 0x10211211, 0x11201110, 0x11201111, 0x11201112,
+    0x11201211, 0x11211010, 0x11211011, 0x11211110, 0x11211111, 0x11211112, 0x11211211, 0x11221011,
+    0x11221110, 0x11221111, 0x11221112, 0x11221211, 0x12201112, 0x12201211, 0x12201212, 0x12211011,
+    0x12211111, 0x12211112, 0x12211211, 0x12211212, 0x12221012, 0x12221111, 0x12221112, 0x12221210,
+    0x10201022, 0x10201221, 0x10211121, 0x10221020, 0x10221122, 0x10221220, 0x10221221, 0x11201020,
+    0x11201121, 0x11201220, 0x11201222, 0x11211021, 0x11211120, 0x11211121, 0x11211122, 0x11211220,
+    0x11211222, 0x11221020, 0x11221121, 0x11221220, 0x12201020, 0x12201022, 0x12201121, 0x12201222,
+    0x12211120, 0x12211122, 0x12211220, 0x12211221, 0x12221020, 0x12221120, 0x12221122, 0x12221222,
+    0x10212102, 0x10212201, 0x10222101, 0x11202001, 0x11212002, 0x11212101, 0x11212202, 0x11222001,
+    0x11222201, 0x12202101, 0x12212001, 0x12212200, 0x12222102, 0x10202011, 0x10202110, 0x10212010,
+    0x10212111, 0x10222011, 0x10222110, 0x10222112, 0x10222211, 0x11202010, 0x11202011, 0x11202111,
+    0x11202112, 0x11202210, 0x11212011, 0x11212110, 0x11212111, 0x11212112, 0x11212211, 0x11222010,
+    0x11222111, 0x11222212, 0x12202012, 0x12202110, 0x12202212, 0x12212111, 0x12222011, 0x12222110,
+    0x12222111, 0x12222211, 0x10212021, 0x10212122, 0x10212220, 0x11202021, 0x11202120, 0x11202221,
+    0x11212020, 0x11212121, 0x11212220, 0x11212222, 0x11222120, 0x11222121, 0x11222221, 0x12202122,
+    0x12212120, 0x12212220, 0x12212222, 0x12222122, 0x20000000, 0x20000002, 0x20000200, 0x20000202,
+    0x20020000, 0x20020002, 0x20020200, 0x20020202, 0x21000101, 0x21010000, 0x21010001, 0x21010100,
+    0x21010102, 0x21010201, 0x21020101, 0x22000000, 0x22000002, 0x22000200, 0x22000202, 0x22010101,
+    0x22020000, 0x22020002, 0x22020200, 0x22020202, 0x20000111, 0x20010011, 0x20010110, 0x20010112,
+    0x20010211, 0x20020111, 0x21000011, 0x21000110, 0x21000211, 0x21010010, 0x21010012, 0x21010111,
+    0x21010112, 0x21010210, 0x21010211, 0x21020110, 0x21020112, 0x21020211, 0x22000111, 0x22000211,
+    0x22010110, 0x22010112, 0x22010211, 0x22020111, 0x20000020, 0x20000022, 0x20000220, 0x20000222,
+    0x20010121, 0x20020020, 0x20020022, 0x20020220, 0x20020222, 0x21010021, 0x21010120, 0x21010221,
+    0x21020121, 0x22000020, 0x22000022, 0x22000220, 0x22000222, 0x22010121, 0x22020020, 0x22020022,
+    0x22020220, 0x22020222, 0x20011100, 0x20011201, 0x21001001, 0x21001100, 0x21011001, 0x21011101,
+    0x21011202, 0x21021001, 0x21021100, 0x21021201, 0x22011100, 0x22011201, 0x20001011, 0x20001211,
+    0x20011012, 0x20011111, 0x20011212, 0x20021112, 0x20021211, 0x21001010, 0x21001011, 0x21001111,
+    0x21001210, 0x21011011, 0x21011110, 0x21011111, 0x21011112, 0x21011211, 0x21011212, 0x21021111,
+    0x21021112, 0x21021210, 0x21021212, 0x22001011, 0x22001110, 0x22001112, 0x22001211, 0x22011010,
+    0x22011012, 0x22011111, 0x22011210, 0x22021112, 0x20011021, 0x20011122, 0x20011221, 0x20021121,
+    0x21001021, 0x21001120, 0x21001221, 0x21001222, 0x21011020, 0x21011121, 0x21011221, 0x21011222,
+    0x21021021, 0x21021122, 0x21021222, 0x22001121, 0x22011021, 0x22011222, 0x22021120, 0x20002000,
+    0x20002002, 0x20002200, 0x20002202, 0x20012101, 0x20022000, 0x20022002, 0x20022200, 0x20022202,
+    0x21002001, 0x21002101, 0x21012001, 0x21012100, 0x21012201, 0x21022101, 0x21022201, 0x22002000,
+    0x22002002, 0x22002200, 0x22002202, 0x22012101, 0x22022000, 0x22022002, 0x22022200, 0x22022202,
+    0x20002111, 0x20002112, 0x20012011, 0x20012110, 0x20012112, 0x20022111, 0x21002011, 0x21002110,
+    0x21002112, 0x21002211, 0x21012010, 0x21012012, 0x21012111, 0x21012212, 0x21022011, 0x21022110,
+    0x22002111, 0x22012112, 0x22012211, 0x22022111, 0x20002020, 0x20002022, 0x20002220, 0x20002222,
+    0x20012121, 0x20022020, 0x20022022, 0x20022220, 0x20022222, 0x21002121, 0x21012021, 0x21012120,
+    0x21012122, 0x22002020, 0x22002022, 0x22002220, 0x22002222, 0x22012121, 0x22022020, 0x22022022,
+    0x22022220, 0x22022222, 0x20100101, 0x20110001, 0x20110102, 0x20110200, 0x20110201, 0x20120101,
+    0x21100001, 0x21100102, 0x21100201, 0x21110101, 0x21110200, 0x21110202, 0x21120201, 0x21120202,
+    0x22100101, 0x22110001, 0x22110100, 0x22110102, 0x22110201, 0x22120101, 0x20100011, 0x20100110,
+    0x20100112, 0x20100211, 0x20110010, 0x20110111, 0x20110210, 0x20110212, 0x20120011, 0x20120110,
+    0x20120112, 0x20120211, 0x21100010, 0x21100111, 0x21110010, 0x21110011, 0x21110110, 0x21110111,
+    0x21110112, 0x21110211, 0x21120012, 0x21120111, 0x22100110, 0x22100112, 0x22110012, 0x22110111,
+    0x22110210, 0x22120011, 0x22120110, 0x22120112, 0x22120211, 0x20100121, 0x20110021, 0x20110120,
+    0x20110221, 0x20120121, 0x21100120, 0x21100122, 0x21100221, 0x21110020, 0x21110022, 0x21110121,
+    0x21110220, 0x21120122, 0x21120221, 0x22100121, 0x22110120, 0x22110122, 0x22120221, 0x20101001,
+    0x20101100, 0x20101102, 0x20111000, 0x20111101, 0x20111200, 0x20121102, 0x21101000, 0x21101202,
+    0x21111001, 0x21111100, 0x21111101, 0x21111102, 0x21111200, 0x21111201, 0x21121000, 0x21121001,
+    0x21121002, 0x21121101, 0x22101100, 0x22101102, 0x22111002, 0x22111100, 0x22111101, 0x22111200,
+    0x22121001, 0x22121201, 0x20101010, 0x20101111, 0x20101210, 0x20101212, 0x20111010, 0x20111011,
+    0x20111110, 0x20111111, 0x20111112, 0x20111211, 0x20121011, 0x20121111, 0x20121211, 0x20121212,
+    0x21101011, 0x21101110, 0x21101111, 0x21101112, 0x21101211, 0x21111010, 0x21111011, 0x21111012,
+    0x21111110, 0x21111111, 0x21111112, 0x21111210, 0x21111211, 0x21111212, 0x21121011, 0x21121110,
+    0x21121111, 0x21121112, 0x21121211, 0x22101011, 0x22101111, 0x22101210, 0x22111011, 0x22111012,
+    0x22111110, 0x22111111, 0x22111112, 0x22111211, 0x22111212, 0x22121010, 0x22121012, 0x22121111,
+    0x22121210, 0x22121212, 0x20101021, 0x20101120, 0x20111020, 0x20111121, 0x20111221, 0x20121020,
+    0x20121122, 0x20121221, 0x21101121, 0x21101220, 0x21101221, 0x21111021, 0x21111022, 0x21111121,
+    0x21111122, 0x21111221, 0x21121121, 0x21121220, 0x22101022, 0x22101120, 0x22101221, 0x22101222,
+    0x22111022, 0x22111120, 0x22111121, 0x22121120, 0x22121122, 0x22121221, 0x20102101, 0x20112102,
+    0x20112201, 0x20122101, 0x21102001, 0x21102102, 0x21112000, 0x21112002, 0x21112101, 0x21112102,
+    0x21112202, 0x21122100, 0x21122101, 0x22102101, 0x22112001, 0x22112102, 0x22112201, 0x22122101,
+    0x20102110, 0x20102112, 0x20102211, 0x20112010, 0x20112012, 0x20112111, 0x20112210, 0x20112212,
+    0x20122010, 0x20122011, 0x20122110, 0x20122112, 0x21102010, 0x21102012, 0x21102111, 0x21102210,
+    0x21102212, 0x21112011, 0x21112110, 0x21112111, 0x21112112, 0x21112211, 0x21122012, 0x21122111,
+    0x21122112, 0x21122212, 0x22102011, 0x22102110, 0x22112010, 0x22112012, 0x22112111, 0x22112212,
+    0x22122011, 0x22122112, 0x20102121, 0x20112121, 0x20122121, 0x21102120, 0x21102122, 0x21102221,
+    0x21112020, 0x21112121, 0x21112220, 0x21122021, 0x22102121, 0x22112021, 0x22112120, 0x22112121,
+    0x22112122, 0x20200000, 0x20200002, 0x20200200, 0x20200202, 0x20210101, 0x20220000, 0x20220002,
+    0x20220200, 0x20220202, 0x21200101, 0x21210001, 0x21210100, 0x21210102, 0x21210201, 0x22200000,
+    0x22200002, 0x22200200, 0x22200202, 0x22210101, 0x22220000, 0x22220002, 0x22220200, 0x22220202,
+    0x20200111, 0x20200211, 0x20210011, 0x20210110, 0x20210112, 0x20210211, 0x20210212, 0x21200112,
+    0x21200211, 0x21210011, 0x21210111, 0x21210210, 0x21210212, 0x21220011, 0x21220110, 0x22200111,
+    0x22210010, 0x22210012, 0x22210112, 0x22210211, 0x20200022, 0x20200220, 0x20200222, 0x20210020,
+    0x20210221, 0x20220022, 0x20220220, 0x20220222, 0x21200121, 0x21210021, 0x21210122, 0x21210221,
+    0x21220121, 0x22200020, 0x22200022, 0x22200220, 0x22200222, 0x22210121, 0x22220020, 0x22220022,
+    0x22220220, 0x22220222, 0x20211201, 0x20221101, 0x21201001, 0x21201100, 0x21211000, 0x21211100,
+    0x21211101, 0x21211200, 0x21211202, 0x21221001, 0x21221101, 0x21221102, 0x21221200, 0x21221201,
+    0x22201101, 0x20201112, 0x20201211, 0x20211010, 0x20211012, 0x20211111, 0x20211210, 0x20221112,
+    0x20221211, 0x21201012, 0x21201111, 0x21211011, 0x21211110, 0x21211111, 0x21211112, 0x21211211,
+    0x21221111, 0x21221212, 0x22201011, 0x22201110, 0x22201111, 0x22201112, 0x22201211, 0x22211012,
+    0x22211111, 0x22211210, 0x20201121, 0x20211021, 0x20211122, 0x20211222, 0x20221021, 0x20221121,
+    0x21201120, 0x21201122, 0x21201222, 0x21211022, 0x21211121, 0x21211122, 0x21211220, 0x21221020,
+    0x21221022, 0x22201122, 0x22211020, 0x22211121, 0x22211122, 0x22211221, 0x22221021, 0x22221120,
+    0x22221122, 0x20202000, 0x20202002, 0x20202200, 0x20202202, 0x20222000, 0x20222002, 0x20222200,
+    0x20222202, 0x21212001, 0x21212100, 0x21212102, 0x21212201, 0x22202000, 0x22202002, 0x22202200,
+    0x22202202, 0x22212101, 0x22222000, 0x22222002, 0x22222200, 0x22222202, 0x20202111, 0x20212110,
+    0x20212211, 0x20222011, 0x20222111, 0x21202011, 0x21212010, 0x21212111, 0x21212212, 0x21222011,
+    0x21222112, 0x21222211, 0x22212010, 0x22212112, 0x20202020, 0x20202022, 0x20202220, 0x20202222,
+    0x20222020, 0x20222022, 0x20222220, 0x20222222, 0x21212021, 0x21212120, 0x21212122, 0x22202020,
+    0x22202022, 0x22202220, 0x22202222, 0x22212121, 0x22222020, 0x22222022, 0x22222220, 0x22222222,
+GGML_TABLE_END()
+#endif
+
+#endif // GGML_COMMON_IMPL
diff --git a/ggml-cuda.cu b/ggml-cuda.cu
index 74562d33c..b5e6181a5 100644
--- a/ggml-cuda.cu
+++ b/ggml-cuda.cu
@@ -2,6 +2,9 @@
 #include "ggml.h"
 #include "ggml-backend-impl.h"
 
+#define GGML_COMMON_IMPL_CUDA
+#include "ggml-common.h"
+
 #include <algorithm>
 #include <assert.h>
 #include <atomic>
@@ -562,8 +565,8 @@ static_assert(sizeof(block_iq3_s) == sizeof(ggml_fp16_t) + 13*(QK_K/32) + IQ3S_N
 #define QI1_S (QK_K / (4*QR1_S))
 typedef struct {
     half d;
-    uint8_t qs[QK_K/8];
-    uint8_t scales[QK_K/16];
+    uint8_t  qs[QK_K/8];
+    uint16_t qh[QK_K/32];
 } block_iq1_s;
 static_assert(sizeof(block_iq1_s) == sizeof(ggml_fp16_t) + QK_K/8 + QK_K/16, "wrong iq1_s block size/padding");
 
@@ -1570,746 +1573,6 @@ static __global__ void dequantize_block_q6_K(const void * __restrict__ vx, dst_t
 #endif
 }
 
-static const __device__ uint64_t iq2xxs_grid[256] = {
-    0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08,
-    0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x08080808082b0808,
-    0x08080808082b082b, 0x08080808082b2b08, 0x08080808082b2b2b, 0x0808080819080819,
-    0x0808080819081908, 0x0808080819190808, 0x0808080819192b08, 0x08080808192b0819,
-    0x08080808192b1908, 0x080808082b080808, 0x080808082b08082b, 0x080808082b082b2b,
-    0x080808082b2b082b, 0x0808081908080819, 0x0808081908081908, 0x0808081908190808,
-    0x0808081908191919, 0x0808081919080808, 0x080808192b081908, 0x080808192b192b08,
-    0x0808082b08080808, 0x0808082b0808082b, 0x0808082b082b082b, 0x0808082b2b08082b,
-    0x0808190808080819, 0x0808190808081908, 0x0808190808190808, 0x08081908082b0819,
-    0x08081908082b1908, 0x0808190819080808, 0x080819081908082b, 0x0808190819082b08,
-    0x08081908192b0808, 0x080819082b080819, 0x080819082b081908, 0x080819082b190808,
-    0x080819082b2b1908, 0x0808191908080808, 0x080819190808082b, 0x0808191908082b08,
-    0x08081919082b0808, 0x080819191908192b, 0x08081919192b2b19, 0x080819192b080808,
-    0x080819192b190819, 0x0808192b08082b19, 0x0808192b08190808, 0x0808192b19080808,
-    0x0808192b2b081908, 0x0808192b2b2b1908, 0x08082b0808080808, 0x08082b0808081919,
-    0x08082b0808082b08, 0x08082b0808191908, 0x08082b08082b2b08, 0x08082b0819080819,
-    0x08082b0819081908, 0x08082b0819190808, 0x08082b081919082b, 0x08082b082b082b08,
-    0x08082b1908081908, 0x08082b1919080808, 0x08082b2b0808082b, 0x08082b2b08191908,
-    0x0819080808080819, 0x0819080808081908, 0x0819080808190808, 0x08190808082b0819,
-    0x0819080819080808, 0x08190808192b0808, 0x081908082b081908, 0x081908082b190808,
-    0x081908082b191919, 0x0819081908080808, 0x0819081908082b08, 0x08190819082b0808,
-    0x0819081919190808, 0x0819081919192b2b, 0x081908192b080808, 0x0819082b082b1908,
-    0x0819082b19081919, 0x0819190808080808, 0x0819190808082b08, 0x08191908082b0808,
-    0x08191908082b1919, 0x0819190819082b19, 0x081919082b080808, 0x0819191908192b08,
-    0x08191919192b082b, 0x0819192b08080808, 0x0819192b0819192b, 0x08192b0808080819,
-    0x08192b0808081908, 0x08192b0808190808, 0x08192b0819080808, 0x08192b082b080819,
-    0x08192b1908080808, 0x08192b1908081919, 0x08192b192b2b0808, 0x08192b2b19190819,
-    0x082b080808080808, 0x082b08080808082b, 0x082b080808082b2b, 0x082b080819081908,
-    0x082b0808192b0819, 0x082b08082b080808, 0x082b08082b08082b, 0x082b0819082b2b19,
-    0x082b081919082b08, 0x082b082b08080808, 0x082b082b0808082b, 0x082b190808080819,
-    0x082b190808081908, 0x082b190808190808, 0x082b190819080808, 0x082b19081919192b,
-    0x082b191908080808, 0x082b191919080819, 0x082b1919192b1908, 0x082b192b2b190808,
-    0x082b2b0808082b08, 0x082b2b08082b0808, 0x082b2b082b191908, 0x082b2b2b19081908,
-    0x1908080808080819, 0x1908080808081908, 0x1908080808190808, 0x1908080808192b08,
-    0x19080808082b0819, 0x19080808082b1908, 0x1908080819080808, 0x1908080819082b08,
-    0x190808081919192b, 0x19080808192b0808, 0x190808082b080819, 0x190808082b081908,
-    0x190808082b190808, 0x1908081908080808, 0x19080819082b0808, 0x19080819192b0819,
-    0x190808192b080808, 0x190808192b081919, 0x1908082b08080819, 0x1908082b08190808,
-    0x1908082b19082b08, 0x1908082b1919192b, 0x1908082b192b2b08, 0x1908190808080808,
-    0x1908190808082b08, 0x19081908082b0808, 0x190819082b080808, 0x190819082b192b19,
-    0x190819190819082b, 0x19081919082b1908, 0x1908192b08080808, 0x19082b0808080819,
-    0x19082b0808081908, 0x19082b0808190808, 0x19082b0819080808, 0x19082b0819081919,
-    0x19082b1908080808, 0x19082b1919192b08, 0x19082b19192b0819, 0x19082b192b08082b,
-    0x19082b2b19081919, 0x19082b2b2b190808, 0x1919080808080808, 0x1919080808082b08,
-    0x1919080808190819, 0x1919080808192b19, 0x19190808082b0808, 0x191908082b080808,
-    0x191908082b082b08, 0x1919081908081908, 0x191908191908082b, 0x191908192b2b1908,
-    0x1919082b2b190819, 0x191919082b190808, 0x191919082b19082b, 0x1919191908082b2b,
-    0x1919192b08080819, 0x1919192b19191908, 0x19192b0808080808, 0x19192b0808190819,
-    0x19192b0808192b19, 0x19192b08192b1908, 0x19192b1919080808, 0x19192b2b08082b08,
-    0x192b080808081908, 0x192b080808190808, 0x192b080819080808, 0x192b0808192b2b08,
-    0x192b081908080808, 0x192b081919191919, 0x192b082b08192b08, 0x192b082b192b0808,
-    0x192b190808080808, 0x192b190808081919, 0x192b191908190808, 0x192b19190819082b,
-    0x192b19192b081908, 0x192b2b081908082b, 0x2b08080808080808, 0x2b0808080808082b,
-    0x2b08080808082b2b, 0x2b08080819080819, 0x2b0808082b08082b, 0x2b08081908081908,
-    0x2b08081908192b08, 0x2b08081919080808, 0x2b08082b08190819, 0x2b08190808080819,
-    0x2b08190808081908, 0x2b08190808190808, 0x2b08190808191919, 0x2b08190819080808,
-    0x2b081908192b0808, 0x2b08191908080808, 0x2b0819191908192b, 0x2b0819192b191908,
-    0x2b08192b08082b19, 0x2b08192b19080808, 0x2b08192b192b0808, 0x2b082b080808082b,
-    0x2b082b1908081908, 0x2b082b2b08190819, 0x2b19080808081908, 0x2b19080808190808,
-    0x2b190808082b1908, 0x2b19080819080808, 0x2b1908082b2b0819, 0x2b1908190819192b,
-    0x2b1908192b080808, 0x2b19082b19081919, 0x2b19190808080808, 0x2b191908082b082b,
-    0x2b19190819081908, 0x2b19191919190819, 0x2b192b082b080819, 0x2b192b19082b0808,
-    0x2b2b08080808082b, 0x2b2b080819190808, 0x2b2b08082b081919, 0x2b2b081908082b19,
-    0x2b2b082b08080808, 0x2b2b190808192b08, 0x2b2b2b0819190808, 0x2b2b2b1908081908,
-};
-
-static const __device__ uint64_t iq2xs_grid[512] = {
-    0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08,
-    0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x080808080819192b,
-    0x0808080808192b19, 0x08080808082b0808, 0x08080808082b082b, 0x08080808082b1919,
-    0x08080808082b2b08, 0x0808080819080819, 0x0808080819081908, 0x080808081908192b,
-    0x0808080819082b19, 0x0808080819190808, 0x080808081919082b, 0x0808080819191919,
-    0x0808080819192b08, 0x08080808192b0819, 0x08080808192b1908, 0x080808082b080808,
-    0x080808082b08082b, 0x080808082b081919, 0x080808082b082b08, 0x080808082b190819,
-    0x080808082b191908, 0x080808082b192b19, 0x080808082b2b0808, 0x0808081908080819,
-    0x0808081908081908, 0x080808190808192b, 0x0808081908082b19, 0x0808081908190808,
-    0x080808190819082b, 0x0808081908191919, 0x0808081908192b08, 0x0808081908192b2b,
-    0x08080819082b0819, 0x08080819082b1908, 0x0808081919080808, 0x080808191908082b,
-    0x0808081919081919, 0x0808081919082b08, 0x0808081919190819, 0x0808081919191908,
-    0x08080819192b0808, 0x08080819192b2b08, 0x080808192b080819, 0x080808192b081908,
-    0x080808192b190808, 0x0808082b08080808, 0x0808082b0808082b, 0x0808082b08081919,
-    0x0808082b08082b08, 0x0808082b08190819, 0x0808082b08191908, 0x0808082b082b0808,
-    0x0808082b19080819, 0x0808082b19081908, 0x0808082b19190808, 0x0808082b19191919,
-    0x0808082b2b080808, 0x0808082b2b082b2b, 0x0808190808080819, 0x0808190808081908,
-    0x080819080808192b, 0x0808190808082b19, 0x0808190808190808, 0x080819080819082b,
-    0x0808190808191919, 0x0808190808192b08, 0x08081908082b0819, 0x08081908082b1908,
-    0x0808190819080808, 0x080819081908082b, 0x0808190819081919, 0x0808190819082b08,
-    0x0808190819190819, 0x0808190819191908, 0x080819081919192b, 0x08081908192b0808,
-    0x080819082b080819, 0x080819082b081908, 0x080819082b190808, 0x0808191908080808,
-    0x080819190808082b, 0x0808191908081919, 0x0808191908082b08, 0x0808191908190819,
-    0x0808191908191908, 0x08081919082b0808, 0x0808191919080819, 0x0808191919081908,
-    0x0808191919190808, 0x08081919192b0819, 0x080819192b080808, 0x0808192b08080819,
-    0x0808192b08081908, 0x0808192b08190808, 0x0808192b082b192b, 0x0808192b19080808,
-    0x0808192b1908082b, 0x0808192b2b081908, 0x08082b0808080808, 0x08082b080808082b,
-    0x08082b0808081919, 0x08082b0808082b08, 0x08082b0808082b2b, 0x08082b0808190819,
-    0x08082b0808191908, 0x08082b08082b0808, 0x08082b08082b1919, 0x08082b0819080819,
-    0x08082b0819081908, 0x08082b0819190808, 0x08082b0819192b08, 0x08082b082b080808,
-    0x08082b082b2b0808, 0x08082b082b2b2b2b, 0x08082b1908080819, 0x08082b1908081908,
-    0x08082b1908190808, 0x08082b1919080808, 0x08082b192b080819, 0x08082b192b082b19,
-    0x08082b2b08080808, 0x08082b2b082b0808, 0x08082b2b082b2b08, 0x08082b2b2b19192b,
-    0x08082b2b2b2b0808, 0x0819080808080819, 0x0819080808081908, 0x081908080808192b,
-    0x0819080808082b19, 0x0819080808190808, 0x081908080819082b, 0x0819080808191919,
-    0x0819080808192b08, 0x08190808082b0819, 0x08190808082b1908, 0x0819080819080808,
-    0x081908081908082b, 0x0819080819081919, 0x0819080819082b08, 0x0819080819190819,
-    0x0819080819191908, 0x08190808192b0808, 0x08190808192b2b2b, 0x081908082b080819,
-    0x081908082b081908, 0x081908082b190808, 0x0819081908080808, 0x081908190808082b,
-    0x0819081908081919, 0x0819081908082b08, 0x0819081908190819, 0x0819081908191908,
-    0x08190819082b0808, 0x0819081919080819, 0x0819081919081908, 0x0819081919190808,
-    0x081908192b080808, 0x081908192b191908, 0x081908192b19192b, 0x0819082b08080819,
-    0x0819082b08081908, 0x0819082b0808192b, 0x0819082b08190808, 0x0819082b19080808,
-    0x0819082b192b0808, 0x0819190808080808, 0x081919080808082b, 0x0819190808081919,
-    0x0819190808082b08, 0x0819190808190819, 0x0819190808191908, 0x08191908082b0808,
-    0x0819190819080819, 0x0819190819081908, 0x0819190819082b19, 0x0819190819190808,
-    0x08191908192b1908, 0x081919082b080808, 0x0819191908080819, 0x0819191908081908,
-    0x0819191908190808, 0x0819191919080808, 0x0819192b08080808, 0x0819192b08191908,
-    0x0819192b19082b19, 0x08192b0808080819, 0x08192b0808081908, 0x08192b0808190808,
-    0x08192b080819082b, 0x08192b0819080808, 0x08192b0819191908, 0x08192b082b08192b,
-    0x08192b1908080808, 0x08192b1908081919, 0x08192b19192b192b, 0x08192b2b19190819,
-    0x08192b2b2b2b2b19, 0x082b080808080808, 0x082b08080808082b, 0x082b080808081919,
-    0x082b080808082b08, 0x082b080808082b2b, 0x082b080808190819, 0x082b080808191908,
-    0x082b0808082b0808, 0x082b080819080819, 0x082b080819081908, 0x082b080819190808,
-    0x082b08082b080808, 0x082b08082b2b0808, 0x082b081908080819, 0x082b081908081908,
-    0x082b081908190808, 0x082b081919080808, 0x082b081919082b08, 0x082b0819192b1919,
-    0x082b082b08080808, 0x082b082b082b082b, 0x082b082b2b080808, 0x082b082b2b2b2b08,
-    0x082b190808080819, 0x082b190808081908, 0x082b190808190808, 0x082b1908082b2b19,
-    0x082b190819080808, 0x082b191908080808, 0x082b191919080819, 0x082b19191919082b,
-    0x082b19192b192b19, 0x082b192b08080819, 0x082b192b08192b2b, 0x082b192b2b2b192b,
-    0x082b2b0808080808, 0x082b2b0808082b08, 0x082b2b0808082b2b, 0x082b2b08082b0808,
-    0x082b2b0819191919, 0x082b2b082b082b08, 0x082b2b082b2b082b, 0x082b2b19192b2b08,
-    0x082b2b192b190808, 0x082b2b2b08082b08, 0x082b2b2b082b0808, 0x082b2b2b2b08082b,
-    0x082b2b2b2b082b08, 0x082b2b2b2b082b2b, 0x1908080808080819, 0x1908080808081908,
-    0x190808080808192b, 0x1908080808082b19, 0x1908080808190808, 0x190808080819082b,
-    0x1908080808191919, 0x1908080808192b08, 0x19080808082b0819, 0x19080808082b1908,
-    0x1908080819080808, 0x190808081908082b, 0x1908080819081919, 0x1908080819082b08,
-    0x1908080819082b2b, 0x1908080819190819, 0x1908080819191908, 0x19080808192b0808,
-    0x19080808192b1919, 0x190808082b080819, 0x190808082b081908, 0x190808082b190808,
-    0x1908081908080808, 0x190808190808082b, 0x1908081908081919, 0x1908081908082b08,
-    0x1908081908190819, 0x1908081908191908, 0x19080819082b0808, 0x1908081919080819,
-    0x1908081919081908, 0x1908081919190808, 0x190808192b080808, 0x190808192b081919,
-    0x190808192b2b082b, 0x1908082b08080819, 0x1908082b08081908, 0x1908082b08190808,
-    0x1908082b0819082b, 0x1908082b082b2b19, 0x1908082b19080808, 0x1908190808080808,
-    0x190819080808082b, 0x1908190808081919, 0x1908190808082b08, 0x1908190808190819,
-    0x1908190808191908, 0x1908190808192b19, 0x19081908082b0808, 0x1908190819080819,
-    0x1908190819081908, 0x1908190819190808, 0x190819082b080808, 0x190819082b191908,
-    0x1908191908080819, 0x1908191908081908, 0x1908191908190808, 0x19081919082b1908,
-    0x1908191919080808, 0x190819192b192b2b, 0x1908192b08080808, 0x1908192b08082b2b,
-    0x1908192b19081908, 0x1908192b19190808, 0x19082b0808080819, 0x19082b0808081908,
-    0x19082b0808190808, 0x19082b0819080808, 0x19082b0819081919, 0x19082b0819191908,
-    0x19082b08192b082b, 0x19082b1908080808, 0x19082b1908190819, 0x19082b1919081908,
-    0x19082b1919190808, 0x19082b19192b2b19, 0x19082b2b08081908, 0x1919080808080808,
-    0x191908080808082b, 0x1919080808081919, 0x1919080808082b08, 0x1919080808190819,
-    0x1919080808191908, 0x19190808082b0808, 0x19190808082b2b08, 0x1919080819080819,
-    0x1919080819081908, 0x1919080819190808, 0x191908082b080808, 0x1919081908080819,
-    0x1919081908081908, 0x1919081908190808, 0x1919081908191919, 0x1919081919080808,
-    0x191908191908082b, 0x1919082b08080808, 0x1919082b19081908, 0x1919082b2b2b2b2b,
-    0x1919190808080819, 0x1919190808081908, 0x1919190808190808, 0x19191908082b0819,
-    0x1919190819080808, 0x19191908192b0808, 0x191919082b080819, 0x191919082b2b0819,
-    0x1919191908080808, 0x1919191908082b08, 0x191919192b080808, 0x191919192b082b08,
-    0x1919192b082b0819, 0x1919192b192b2b08, 0x1919192b2b2b0819, 0x19192b0808080808,
-    0x19192b0808191908, 0x19192b0819080819, 0x19192b0819190808, 0x19192b082b192b19,
-    0x19192b1908192b2b, 0x19192b1919080808, 0x19192b191908082b, 0x19192b2b2b081919,
-    0x192b080808080819, 0x192b080808081908, 0x192b080808190808, 0x192b080819080808,
-    0x192b080819191908, 0x192b0808192b082b, 0x192b08082b08192b, 0x192b08082b2b2b19,
-    0x192b081908080808, 0x192b082b082b1908, 0x192b082b19082b2b, 0x192b082b2b19082b,
-    0x192b190808080808, 0x192b19080819192b, 0x192b191908190808, 0x192b191919080808,
-    0x192b191919081919, 0x192b19192b2b1908, 0x192b2b0808080819, 0x192b2b08192b2b2b,
-    0x192b2b19082b1919, 0x192b2b2b0808192b, 0x192b2b2b19191908, 0x192b2b2b192b082b,
-    0x2b08080808080808, 0x2b0808080808082b, 0x2b08080808081919, 0x2b08080808082b08,
-    0x2b08080808190819, 0x2b08080808191908, 0x2b080808082b0808, 0x2b080808082b2b2b,
-    0x2b08080819080819, 0x2b08080819081908, 0x2b08080819190808, 0x2b0808082b080808,
-    0x2b0808082b08082b, 0x2b0808082b2b2b08, 0x2b0808082b2b2b2b, 0x2b08081908080819,
-    0x2b08081908081908, 0x2b0808190808192b, 0x2b08081908190808, 0x2b08081919080808,
-    0x2b08081919190819, 0x2b08081919192b19, 0x2b08082b08080808, 0x2b08082b082b0808,
-    0x2b08082b2b080808, 0x2b08082b2b08082b, 0x2b08082b2b2b0808, 0x2b08082b2b2b2b08,
-    0x2b08190808080819, 0x2b08190808081908, 0x2b08190808190808, 0x2b0819080819082b,
-    0x2b08190808191919, 0x2b08190819080808, 0x2b081908192b0808, 0x2b0819082b082b19,
-    0x2b08191908080808, 0x2b08191919081908, 0x2b0819192b2b1919, 0x2b08192b08192b08,
-    0x2b08192b192b2b2b, 0x2b082b0808080808, 0x2b082b0808082b08, 0x2b082b08082b1919,
-    0x2b082b0819192b2b, 0x2b082b082b080808, 0x2b082b082b08082b, 0x2b082b082b2b2b08,
-    0x2b082b190808192b, 0x2b082b2b082b082b, 0x2b082b2b2b080808, 0x2b082b2b2b082b08,
-    0x2b082b2b2b19192b, 0x2b082b2b2b2b2b08, 0x2b19080808080819, 0x2b19080808081908,
-    0x2b19080808190808, 0x2b19080819080808, 0x2b1908081919192b, 0x2b1908082b081908,
-    0x2b19081908080808, 0x2b190819082b082b, 0x2b190819192b1908, 0x2b19082b1919192b,
-    0x2b19082b2b082b19, 0x2b19190808080808, 0x2b19190808081919, 0x2b19190819081908,
-    0x2b19190819190808, 0x2b19190819192b08, 0x2b191919082b2b19, 0x2b1919192b190808,
-    0x2b1919192b19082b, 0x2b19192b19080819, 0x2b192b0819190819, 0x2b192b082b2b192b,
-    0x2b192b1919082b19, 0x2b192b2b08191919, 0x2b192b2b192b0808, 0x2b2b080808080808,
-    0x2b2b08080808082b, 0x2b2b080808082b08, 0x2b2b080808082b2b, 0x2b2b0808082b0808,
-    0x2b2b0808082b2b2b, 0x2b2b08082b2b0808, 0x2b2b081919190819, 0x2b2b081919192b19,
-    0x2b2b08192b2b192b, 0x2b2b082b08080808, 0x2b2b082b0808082b, 0x2b2b082b08082b08,
-    0x2b2b082b082b2b2b, 0x2b2b082b2b080808, 0x2b2b082b2b2b0808, 0x2b2b190819080808,
-    0x2b2b19082b191919, 0x2b2b192b192b1919, 0x2b2b192b2b192b08, 0x2b2b2b0808082b2b,
-    0x2b2b2b08082b0808, 0x2b2b2b08082b082b, 0x2b2b2b08082b2b08, 0x2b2b2b082b2b0808,
-    0x2b2b2b082b2b2b08, 0x2b2b2b1908081908, 0x2b2b2b192b081908, 0x2b2b2b192b08192b,
-    0x2b2b2b2b082b2b08, 0x2b2b2b2b082b2b2b, 0x2b2b2b2b2b190819, 0x2b2b2b2b2b2b2b2b,
-};
-
-static const __device__ uint64_t iq2s_grid[1024] = {
-    0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08,
-    0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x080808080819192b,
-    0x0808080808192b19, 0x08080808082b0808, 0x08080808082b082b, 0x08080808082b1919,
-    0x08080808082b2b08, 0x0808080819080819, 0x0808080819081908, 0x080808081908192b,
-    0x0808080819082b19, 0x0808080819190808, 0x080808081919082b, 0x0808080819191919,
-    0x0808080819192b08, 0x08080808192b0819, 0x08080808192b1908, 0x08080808192b192b,
-    0x08080808192b2b19, 0x080808082b080808, 0x080808082b08082b, 0x080808082b081919,
-    0x080808082b082b08, 0x080808082b190819, 0x080808082b191908, 0x080808082b2b0808,
-    0x080808082b2b1919, 0x080808082b2b2b2b, 0x0808081908080819, 0x0808081908081908,
-    0x080808190808192b, 0x0808081908082b19, 0x0808081908190808, 0x080808190819082b,
-    0x0808081908191919, 0x0808081908192b08, 0x08080819082b0819, 0x08080819082b1908,
-    0x0808081919080808, 0x080808191908082b, 0x0808081919081919, 0x0808081919082b08,
-    0x0808081919190819, 0x0808081919191908, 0x080808191919192b, 0x0808081919192b19,
-    0x08080819192b0808, 0x08080819192b1919, 0x08080819192b2b08, 0x080808192b080819,
-    0x080808192b081908, 0x080808192b190808, 0x080808192b19082b, 0x080808192b191919,
-    0x080808192b2b0819, 0x080808192b2b1908, 0x0808082b08080808, 0x0808082b0808082b,
-    0x0808082b08081919, 0x0808082b08082b08, 0x0808082b08190819, 0x0808082b08191908,
-    0x0808082b082b0808, 0x0808082b082b2b2b, 0x0808082b19080819, 0x0808082b19081908,
-    0x0808082b1908192b, 0x0808082b19082b19, 0x0808082b19190808, 0x0808082b19191919,
-    0x0808082b2b080808, 0x0808082b2b081919, 0x0808082b2b082b2b, 0x0808082b2b191908,
-    0x0808082b2b2b082b, 0x0808190808080819, 0x0808190808081908, 0x080819080808192b,
-    0x0808190808082b19, 0x0808190808190808, 0x080819080819082b, 0x0808190808191919,
-    0x0808190808192b08, 0x08081908082b0819, 0x08081908082b1908, 0x08081908082b192b,
-    0x08081908082b2b19, 0x0808190819080808, 0x080819081908082b, 0x0808190819081919,
-    0x0808190819082b08, 0x0808190819082b2b, 0x0808190819190819, 0x0808190819191908,
-    0x080819081919192b, 0x0808190819192b19, 0x08081908192b0808, 0x08081908192b082b,
-    0x08081908192b1919, 0x080819082b080819, 0x080819082b081908, 0x080819082b08192b,
-    0x080819082b082b19, 0x080819082b190808, 0x080819082b191919, 0x080819082b192b08,
-    0x080819082b2b0819, 0x080819082b2b1908, 0x0808191908080808, 0x080819190808082b,
-    0x0808191908081919, 0x0808191908082b08, 0x0808191908082b2b, 0x0808191908190819,
-    0x0808191908191908, 0x080819190819192b, 0x0808191908192b19, 0x08081919082b0808,
-    0x08081919082b1919, 0x08081919082b2b08, 0x0808191919080819, 0x0808191919081908,
-    0x080819191908192b, 0x0808191919082b19, 0x0808191919190808, 0x080819191919082b,
-    0x0808191919191919, 0x0808191919192b08, 0x08081919192b0819, 0x08081919192b1908,
-    0x080819192b080808, 0x080819192b08082b, 0x080819192b081919, 0x080819192b082b08,
-    0x080819192b190819, 0x080819192b191908, 0x080819192b2b0808, 0x0808192b08080819,
-    0x0808192b08081908, 0x0808192b0808192b, 0x0808192b08082b19, 0x0808192b08190808,
-    0x0808192b08191919, 0x0808192b19080808, 0x0808192b19081919, 0x0808192b19082b08,
-    0x0808192b19190819, 0x0808192b19191908, 0x0808192b192b0808, 0x0808192b2b080819,
-    0x0808192b2b081908, 0x0808192b2b190808, 0x08082b0808080808, 0x08082b080808082b,
-    0x08082b0808081919, 0x08082b0808082b08, 0x08082b0808190819, 0x08082b0808191908,
-    0x08082b080819192b, 0x08082b0808192b19, 0x08082b08082b0808, 0x08082b08082b1919,
-    0x08082b08082b2b2b, 0x08082b0819080819, 0x08082b0819081908, 0x08082b081908192b,
-    0x08082b0819082b19, 0x08082b0819190808, 0x08082b081919082b, 0x08082b0819191919,
-    0x08082b0819192b08, 0x08082b08192b0819, 0x08082b08192b1908, 0x08082b082b080808,
-    0x08082b082b081919, 0x08082b082b191908, 0x08082b082b2b2b2b, 0x08082b1908080819,
-    0x08082b1908081908, 0x08082b1908190808, 0x08082b190819082b, 0x08082b1908191919,
-    0x08082b1908192b08, 0x08082b19082b0819, 0x08082b1919080808, 0x08082b1919081919,
-    0x08082b1919082b08, 0x08082b1919190819, 0x08082b1919191908, 0x08082b19192b0808,
-    0x08082b192b080819, 0x08082b192b190808, 0x08082b2b08080808, 0x08082b2b08190819,
-    0x08082b2b08191908, 0x08082b2b082b082b, 0x08082b2b082b2b08, 0x08082b2b082b2b2b,
-    0x08082b2b19190808, 0x08082b2b2b192b19, 0x0819080808080819, 0x0819080808081908,
-    0x081908080808192b, 0x0819080808082b19, 0x0819080808190808, 0x081908080819082b,
-    0x0819080808191919, 0x0819080808192b08, 0x08190808082b0819, 0x08190808082b1908,
-    0x08190808082b192b, 0x0819080819080808, 0x081908081908082b, 0x0819080819081919,
-    0x0819080819082b08, 0x0819080819190819, 0x0819080819191908, 0x081908081919192b,
-    0x0819080819192b19, 0x08190808192b0808, 0x08190808192b082b, 0x08190808192b1919,
-    0x08190808192b2b08, 0x081908082b080819, 0x081908082b081908, 0x081908082b08192b,
-    0x081908082b190808, 0x081908082b191919, 0x081908082b192b08, 0x081908082b2b0819,
-    0x081908082b2b1908, 0x0819081908080808, 0x081908190808082b, 0x0819081908081919,
-    0x0819081908082b08, 0x0819081908082b2b, 0x0819081908190819, 0x0819081908191908,
-    0x081908190819192b, 0x0819081908192b19, 0x08190819082b0808, 0x08190819082b082b,
-    0x08190819082b1919, 0x08190819082b2b08, 0x0819081919080819, 0x0819081919081908,
-    0x081908191908192b, 0x0819081919082b19, 0x0819081919190808, 0x081908191919082b,
-    0x0819081919191919, 0x0819081919192b08, 0x08190819192b0819, 0x08190819192b1908,
-    0x081908192b080808, 0x081908192b08082b, 0x081908192b081919, 0x081908192b082b08,
-    0x081908192b190819, 0x081908192b191908, 0x0819082b08080819, 0x0819082b08081908,
-    0x0819082b08082b19, 0x0819082b08190808, 0x0819082b08191919, 0x0819082b082b0819,
-    0x0819082b082b1908, 0x0819082b19080808, 0x0819082b19081919, 0x0819082b19190819,
-    0x0819082b19191908, 0x0819082b2b080819, 0x0819082b2b081908, 0x0819082b2b190808,
-    0x0819190808080808, 0x081919080808082b, 0x0819190808081919, 0x0819190808082b08,
-    0x0819190808190819, 0x0819190808191908, 0x081919080819192b, 0x0819190808192b19,
-    0x08191908082b0808, 0x08191908082b1919, 0x08191908082b2b08, 0x0819190819080819,
-    0x0819190819081908, 0x081919081908192b, 0x0819190819082b19, 0x0819190819190808,
-    0x081919081919082b, 0x0819190819191919, 0x0819190819192b08, 0x08191908192b0819,
-    0x08191908192b1908, 0x081919082b080808, 0x081919082b08082b, 0x081919082b081919,
-    0x081919082b082b08, 0x081919082b190819, 0x081919082b191908, 0x081919082b2b0808,
-    0x0819191908080819, 0x0819191908081908, 0x081919190808192b, 0x0819191908082b19,
-    0x0819191908190808, 0x081919190819082b, 0x0819191908191919, 0x0819191908192b08,
-    0x08191919082b0819, 0x08191919082b1908, 0x0819191919080808, 0x081919191908082b,
-    0x0819191919081919, 0x0819191919082b08, 0x0819191919190819, 0x0819191919191908,
-    0x08191919192b0808, 0x081919192b080819, 0x081919192b081908, 0x081919192b190808,
-    0x0819192b08080808, 0x0819192b08081919, 0x0819192b08082b08, 0x0819192b08190819,
-    0x0819192b08191908, 0x0819192b082b0808, 0x0819192b19080819, 0x0819192b19081908,
-    0x0819192b19190808, 0x0819192b2b080808, 0x0819192b2b2b2b2b, 0x08192b0808080819,
-    0x08192b0808081908, 0x08192b080808192b, 0x08192b0808082b19, 0x08192b0808190808,
-    0x08192b0808191919, 0x08192b0808192b08, 0x08192b08082b0819, 0x08192b0819080808,
-    0x08192b081908082b, 0x08192b0819081919, 0x08192b0819082b08, 0x08192b0819190819,
-    0x08192b0819191908, 0x08192b08192b0808, 0x08192b082b080819, 0x08192b082b081908,
-    0x08192b1908080808, 0x08192b190808082b, 0x08192b1908081919, 0x08192b1908082b08,
-    0x08192b1908190819, 0x08192b1908191908, 0x08192b19082b0808, 0x08192b1919080819,
-    0x08192b1919081908, 0x08192b1919190808, 0x08192b19192b2b19, 0x08192b192b2b082b,
-    0x08192b2b08081908, 0x08192b2b08190808, 0x08192b2b19080808, 0x08192b2b1919192b,
-    0x082b080808080808, 0x082b08080808082b, 0x082b080808081919, 0x082b080808082b08,
-    0x082b080808190819, 0x082b080808191908, 0x082b08080819192b, 0x082b080808192b19,
-    0x082b0808082b0808, 0x082b0808082b1919, 0x082b0808082b2b2b, 0x082b080819080819,
-    0x082b080819081908, 0x082b080819190808, 0x082b08081919082b, 0x082b080819191919,
-    0x082b0808192b1908, 0x082b08082b080808, 0x082b08082b082b2b, 0x082b08082b191908,
-    0x082b08082b2b2b2b, 0x082b081908080819, 0x082b081908081908, 0x082b081908190808,
-    0x082b08190819082b, 0x082b081908191919, 0x082b0819082b0819, 0x082b081919080808,
-    0x082b08191908082b, 0x082b081919081919, 0x082b081919190819, 0x082b081919191908,
-    0x082b0819192b0808, 0x082b08192b080819, 0x082b08192b081908, 0x082b08192b190808,
-    0x082b082b08080808, 0x082b082b08082b2b, 0x082b082b082b082b, 0x082b082b082b2b08,
-    0x082b082b082b2b2b, 0x082b082b19081908, 0x082b082b19190808, 0x082b082b2b082b08,
-    0x082b082b2b082b2b, 0x082b082b2b2b2b08, 0x082b190808080819, 0x082b190808081908,
-    0x082b19080808192b, 0x082b190808082b19, 0x082b190808190808, 0x082b190808191919,
-    0x082b190808192b08, 0x082b1908082b0819, 0x082b1908082b1908, 0x082b190819080808,
-    0x082b19081908082b, 0x082b190819081919, 0x082b190819082b08, 0x082b190819190819,
-    0x082b190819191908, 0x082b1908192b0808, 0x082b19082b080819, 0x082b19082b081908,
-    0x082b19082b190808, 0x082b191908080808, 0x082b191908081919, 0x082b191908082b08,
-    0x082b191908190819, 0x082b191908191908, 0x082b1919082b0808, 0x082b191919080819,
-    0x082b191919081908, 0x082b191919190808, 0x082b1919192b192b, 0x082b19192b080808,
-    0x082b192b08080819, 0x082b192b08081908, 0x082b192b08190808, 0x082b192b19080808,
-    0x082b192b19192b19, 0x082b2b0808080808, 0x082b2b0808081919, 0x082b2b0808190819,
-    0x082b2b0808191908, 0x082b2b0819080819, 0x082b2b0819081908, 0x082b2b0819190808,
-    0x082b2b082b082b2b, 0x082b2b082b2b2b2b, 0x082b2b1908080819, 0x082b2b1908081908,
-    0x082b2b1908190808, 0x082b2b192b191919, 0x082b2b2b08082b2b, 0x082b2b2b082b082b,
-    0x082b2b2b192b1908, 0x082b2b2b2b082b08, 0x082b2b2b2b082b2b, 0x1908080808080819,
-    0x1908080808081908, 0x190808080808192b, 0x1908080808082b19, 0x1908080808190808,
-    0x190808080819082b, 0x1908080808191919, 0x1908080808192b08, 0x1908080808192b2b,
-    0x19080808082b0819, 0x19080808082b1908, 0x19080808082b192b, 0x1908080819080808,
-    0x190808081908082b, 0x1908080819081919, 0x1908080819082b08, 0x1908080819082b2b,
-    0x1908080819190819, 0x1908080819191908, 0x190808081919192b, 0x1908080819192b19,
-    0x19080808192b0808, 0x19080808192b082b, 0x19080808192b1919, 0x190808082b080819,
-    0x190808082b081908, 0x190808082b190808, 0x190808082b191919, 0x190808082b192b08,
-    0x190808082b2b0819, 0x190808082b2b1908, 0x1908081908080808, 0x190808190808082b,
-    0x1908081908081919, 0x1908081908082b08, 0x1908081908190819, 0x1908081908191908,
-    0x190808190819192b, 0x1908081908192b19, 0x19080819082b0808, 0x19080819082b082b,
-    0x19080819082b1919, 0x1908081919080819, 0x1908081919081908, 0x190808191908192b,
-    0x1908081919082b19, 0x1908081919190808, 0x190808191919082b, 0x1908081919191919,
-    0x1908081919192b08, 0x19080819192b0819, 0x19080819192b1908, 0x190808192b080808,
-    0x190808192b08082b, 0x190808192b081919, 0x190808192b082b08, 0x190808192b190819,
-    0x190808192b191908, 0x190808192b2b0808, 0x1908082b08080819, 0x1908082b08081908,
-    0x1908082b08190808, 0x1908082b0819082b, 0x1908082b08191919, 0x1908082b08192b08,
-    0x1908082b082b1908, 0x1908082b19080808, 0x1908082b19081919, 0x1908082b19082b08,
-    0x1908082b19190819, 0x1908082b19191908, 0x1908082b192b0808, 0x1908082b2b080819,
-    0x1908082b2b081908, 0x1908190808080808, 0x190819080808082b, 0x1908190808081919,
-    0x1908190808082b08, 0x1908190808082b2b, 0x1908190808190819, 0x1908190808191908,
-    0x190819080819192b, 0x1908190808192b19, 0x19081908082b0808, 0x19081908082b082b,
-    0x19081908082b1919, 0x19081908082b2b08, 0x1908190819080819, 0x1908190819081908,
-    0x190819081908192b, 0x1908190819082b19, 0x1908190819190808, 0x190819081919082b,
-    0x1908190819191919, 0x1908190819192b08, 0x19081908192b0819, 0x19081908192b1908,
-    0x190819082b080808, 0x190819082b08082b, 0x190819082b081919, 0x190819082b082b08,
-    0x190819082b190819, 0x190819082b191908, 0x190819082b2b0808, 0x1908191908080819,
-    0x1908191908081908, 0x190819190808192b, 0x1908191908082b19, 0x1908191908190808,
-    0x190819190819082b, 0x1908191908191919, 0x1908191908192b08, 0x19081919082b0819,
-    0x19081919082b1908, 0x1908191919080808, 0x190819191908082b, 0x1908191919081919,
-    0x1908191919082b08, 0x1908191919190819, 0x1908191919191908, 0x19081919192b0808,
-    0x19081919192b2b2b, 0x190819192b080819, 0x190819192b081908, 0x190819192b190808,
-    0x1908192b08080808, 0x1908192b0808082b, 0x1908192b08081919, 0x1908192b08082b08,
-    0x1908192b08190819, 0x1908192b08191908, 0x1908192b082b0808, 0x1908192b19080819,
-    0x1908192b19081908, 0x1908192b19190808, 0x1908192b2b080808, 0x1908192b2b2b1919,
-    0x19082b0808080819, 0x19082b0808081908, 0x19082b0808082b19, 0x19082b0808190808,
-    0x19082b080819082b, 0x19082b0808191919, 0x19082b0808192b08, 0x19082b08082b0819,
-    0x19082b08082b1908, 0x19082b0819080808, 0x19082b081908082b, 0x19082b0819081919,
-    0x19082b0819082b08, 0x19082b0819190819, 0x19082b0819191908, 0x19082b08192b0808,
-    0x19082b082b081908, 0x19082b082b190808, 0x19082b1908080808, 0x19082b190808082b,
-    0x19082b1908081919, 0x19082b1908082b08, 0x19082b1908190819, 0x19082b1908191908,
-    0x19082b19082b0808, 0x19082b1919080819, 0x19082b1919081908, 0x19082b1919190808,
-    0x19082b192b080808, 0x19082b192b19192b, 0x19082b2b08080819, 0x19082b2b08081908,
-    0x19082b2b08190808, 0x19082b2b19080808, 0x1919080808080808, 0x191908080808082b,
-    0x1919080808081919, 0x1919080808082b08, 0x1919080808190819, 0x1919080808191908,
-    0x191908080819192b, 0x1919080808192b19, 0x19190808082b0808, 0x19190808082b082b,
-    0x19190808082b1919, 0x19190808082b2b08, 0x1919080819080819, 0x1919080819081908,
-    0x191908081908192b, 0x1919080819082b19, 0x1919080819190808, 0x191908081919082b,
-    0x1919080819191919, 0x1919080819192b08, 0x19190808192b0819, 0x19190808192b1908,
-    0x191908082b080808, 0x191908082b08082b, 0x191908082b081919, 0x191908082b082b08,
-    0x191908082b190819, 0x191908082b191908, 0x1919081908080819, 0x1919081908081908,
-    0x191908190808192b, 0x1919081908082b19, 0x1919081908190808, 0x191908190819082b,
-    0x1919081908191919, 0x1919081908192b08, 0x19190819082b0819, 0x19190819082b1908,
-    0x1919081919080808, 0x191908191908082b, 0x1919081919081919, 0x1919081919082b08,
-    0x1919081919190819, 0x1919081919191908, 0x19190819192b0808, 0x191908192b080819,
-    0x191908192b081908, 0x191908192b190808, 0x1919082b08080808, 0x1919082b08081919,
-    0x1919082b08082b08, 0x1919082b08190819, 0x1919082b08191908, 0x1919082b082b0808,
-    0x1919082b19080819, 0x1919082b19081908, 0x1919082b19190808, 0x1919082b192b2b19,
-    0x1919082b2b080808, 0x1919190808080819, 0x1919190808081908, 0x191919080808192b,
-    0x1919190808082b19, 0x1919190808190808, 0x191919080819082b, 0x1919190808191919,
-    0x1919190808192b08, 0x19191908082b0819, 0x19191908082b1908, 0x1919190819080808,
-    0x191919081908082b, 0x1919190819081919, 0x1919190819082b08, 0x1919190819190819,
-    0x1919190819191908, 0x19191908192b0808, 0x191919082b080819, 0x191919082b081908,
-    0x191919082b190808, 0x1919191908080808, 0x191919190808082b, 0x1919191908081919,
-    0x1919191908082b08, 0x1919191908190819, 0x1919191908191908, 0x19191919082b0808,
-    0x1919191919080819, 0x1919191919081908, 0x1919191919190808, 0x191919192b080808,
-    0x1919192b08080819, 0x1919192b08081908, 0x1919192b08190808, 0x1919192b082b192b,
-    0x1919192b19080808, 0x19192b0808080808, 0x19192b080808082b, 0x19192b0808081919,
-    0x19192b0808082b08, 0x19192b0808190819, 0x19192b0808191908, 0x19192b08082b0808,
-    0x19192b0819080819, 0x19192b0819081908, 0x19192b0819190808, 0x19192b0819192b2b,
-    0x19192b082b080808, 0x19192b1908080819, 0x19192b1908081908, 0x19192b1908190808,
-    0x19192b1919080808, 0x19192b2b08080808, 0x19192b2b08192b19, 0x19192b2b2b081919,
-    0x19192b2b2b2b2b08, 0x192b080808080819, 0x192b080808081908, 0x192b08080808192b,
-    0x192b080808190808, 0x192b08080819082b, 0x192b080808191919, 0x192b080808192b08,
-    0x192b0808082b0819, 0x192b0808082b1908, 0x192b080819080808, 0x192b080819081919,
-    0x192b080819082b08, 0x192b080819190819, 0x192b080819191908, 0x192b0808192b0808,
-    0x192b08082b081908, 0x192b08082b190808, 0x192b081908080808, 0x192b08190808082b,
-    0x192b081908081919, 0x192b081908082b08, 0x192b081908190819, 0x192b081908191908,
-    0x192b0819082b0808, 0x192b081919080819, 0x192b081919081908, 0x192b081919190808,
-    0x192b08192b080808, 0x192b08192b192b19, 0x192b082b08081908, 0x192b082b08190808,
-    0x192b082b19080808, 0x192b082b1919192b, 0x192b082b2b2b0819, 0x192b190808080808,
-    0x192b190808081919, 0x192b190808082b08, 0x192b190808190819, 0x192b190808191908,
-    0x192b1908082b0808, 0x192b190819080819, 0x192b190819081908, 0x192b190819190808,
-    0x192b19082b080808, 0x192b191908080819, 0x192b191908081908, 0x192b191908190808,
-    0x192b191919080808, 0x192b191919082b2b, 0x192b1919192b2b08, 0x192b19192b19082b,
-    0x192b192b08080808, 0x192b192b2b191908, 0x192b2b0808080819, 0x192b2b0808081908,
-    0x192b2b0808190808, 0x192b2b08192b1919, 0x192b2b082b192b08, 0x192b2b1908080808,
-    0x192b2b19082b2b2b, 0x192b2b2b1908082b, 0x192b2b2b2b2b0819, 0x2b08080808080808,
-    0x2b0808080808082b, 0x2b08080808081919, 0x2b08080808082b08, 0x2b08080808190819,
-    0x2b08080808191908, 0x2b08080808192b19, 0x2b080808082b0808, 0x2b080808082b1919,
-    0x2b08080819080819, 0x2b08080819081908, 0x2b08080819190808, 0x2b0808081919082b,
-    0x2b08080819191919, 0x2b08080819192b08, 0x2b080808192b0819, 0x2b0808082b080808,
-    0x2b0808082b081919, 0x2b0808082b190819, 0x2b0808082b191908, 0x2b08081908080819,
-    0x2b08081908081908, 0x2b08081908082b19, 0x2b08081908190808, 0x2b0808190819082b,
-    0x2b08081908191919, 0x2b08081908192b08, 0x2b080819082b0819, 0x2b080819082b1908,
-    0x2b08081919080808, 0x2b0808191908082b, 0x2b08081919081919, 0x2b08081919082b08,
-    0x2b08081919190819, 0x2b08081919191908, 0x2b0808192b080819, 0x2b0808192b081908,
-    0x2b0808192b190808, 0x2b0808192b2b2b19, 0x2b08082b08080808, 0x2b08082b08081919,
-    0x2b08082b08082b2b, 0x2b08082b08190819, 0x2b08082b08191908, 0x2b08082b19080819,
-    0x2b08082b19081908, 0x2b08082b19190808, 0x2b08190808080819, 0x2b08190808081908,
-    0x2b0819080808192b, 0x2b08190808082b19, 0x2b08190808190808, 0x2b0819080819082b,
-    0x2b08190808191919, 0x2b08190808192b08, 0x2b081908082b0819, 0x2b08190819080808,
-    0x2b0819081908082b, 0x2b08190819081919, 0x2b08190819082b08, 0x2b08190819190819,
-    0x2b08190819191908, 0x2b081908192b0808, 0x2b0819082b080819, 0x2b0819082b081908,
-    0x2b0819082b190808, 0x2b08191908080808, 0x2b0819190808082b, 0x2b08191908081919,
-    0x2b08191908082b08, 0x2b08191908190819, 0x2b08191908191908, 0x2b081919082b0808,
-    0x2b08191919080819, 0x2b08191919081908, 0x2b08191919190808, 0x2b0819192b080808,
-    0x2b0819192b082b2b, 0x2b08192b08080819, 0x2b08192b08081908, 0x2b08192b08190808,
-    0x2b08192b082b2b19, 0x2b08192b19080808, 0x2b082b0808080808, 0x2b082b0808081919,
-    0x2b082b0808190819, 0x2b082b0808191908, 0x2b082b0819080819, 0x2b082b0819081908,
-    0x2b082b0819190808, 0x2b082b082b2b082b, 0x2b082b1908080819, 0x2b082b1908081908,
-    0x2b082b1919080808, 0x2b082b19192b1919, 0x2b082b2b082b082b, 0x2b082b2b19192b08,
-    0x2b082b2b19192b2b, 0x2b082b2b2b08082b, 0x2b082b2b2b2b082b, 0x2b19080808080819,
-    0x2b19080808081908, 0x2b19080808082b19, 0x2b19080808190808, 0x2b1908080819082b,
-    0x2b19080808191919, 0x2b19080808192b08, 0x2b190808082b1908, 0x2b19080819080808,
-    0x2b1908081908082b, 0x2b19080819081919, 0x2b19080819082b08, 0x2b19080819190819,
-    0x2b19080819191908, 0x2b190808192b0808, 0x2b1908082b080819, 0x2b1908082b081908,
-    0x2b1908082b190808, 0x2b19081908080808, 0x2b19081908081919, 0x2b19081908190819,
-    0x2b19081908191908, 0x2b19081919080819, 0x2b19081919081908, 0x2b19081919190808,
-    0x2b19081919192b2b, 0x2b19082b08080819, 0x2b19082b08081908, 0x2b19082b08190808,
-    0x2b19082b19080808, 0x2b19082b2b2b192b, 0x2b19190808080808, 0x2b1919080808082b,
-    0x2b19190808081919, 0x2b19190808082b08, 0x2b19190808190819, 0x2b19190808191908,
-    0x2b191908082b0808, 0x2b19190819080819, 0x2b19190819081908, 0x2b19190819190808,
-    0x2b1919082b080808, 0x2b1919082b19192b, 0x2b19191908080819, 0x2b19191908081908,
-    0x2b19191908190808, 0x2b19191919080808, 0x2b1919192b192b08, 0x2b1919192b2b0819,
-    0x2b19192b08080808, 0x2b19192b1908192b, 0x2b19192b192b1908, 0x2b192b0808080819,
-    0x2b192b0808081908, 0x2b192b0808190808, 0x2b192b08082b192b, 0x2b192b0819080808,
-    0x2b192b082b2b2b19, 0x2b192b1908080808, 0x2b192b1919082b19, 0x2b192b191919082b,
-    0x2b192b2b2b190808, 0x2b2b080808080808, 0x2b2b080808081919, 0x2b2b080808082b2b,
-    0x2b2b080808191908, 0x2b2b0808082b082b, 0x2b2b0808082b2b2b, 0x2b2b080819080819,
-    0x2b2b080819081908, 0x2b2b080819190808, 0x2b2b08082b2b082b, 0x2b2b08082b2b2b2b,
-    0x2b2b081919080808, 0x2b2b0819192b1919, 0x2b2b082b0808082b, 0x2b2b082b08082b2b,
-    0x2b2b082b082b082b, 0x2b2b082b082b2b08, 0x2b2b082b082b2b2b, 0x2b2b082b2b08082b,
-    0x2b2b082b2b082b08, 0x2b2b082b2b082b2b, 0x2b2b082b2b2b2b08, 0x2b2b190808080819,
-    0x2b2b190808081908, 0x2b2b190808190808, 0x2b2b190819080808, 0x2b2b19082b082b19,
-    0x2b2b19082b2b1908, 0x2b2b191908080808, 0x2b2b191908192b19, 0x2b2b192b19190819,
-    0x2b2b2b0808082b2b, 0x2b2b2b08082b2b08, 0x2b2b2b082b2b082b, 0x2b2b2b1919191908,
-    0x2b2b2b192b08192b, 0x2b2b2b2b08082b08, 0x2b2b2b2b08082b2b, 0x2b2b2b2b082b0808,
-    0x2b2b2b2b082b082b, 0x2b2b2b2b082b2b08, 0x2b2b2b2b2b082b08, 0x2b2b2b2b2b2b2b2b,
-};
-
-static const __device__ uint32_t iq3xxs_grid[256] = {
-    0x04040404, 0x04040414, 0x04040424, 0x04040c0c, 0x04040c1c, 0x04040c3e, 0x04041404, 0x04041414,
-    0x04041c0c, 0x04042414, 0x04043e1c, 0x04043e2c, 0x040c040c, 0x040c041c, 0x040c0c04, 0x040c0c14,
-    0x040c140c, 0x040c142c, 0x040c1c04, 0x040c1c14, 0x040c240c, 0x040c2c24, 0x040c3e04, 0x04140404,
-    0x04140414, 0x04140424, 0x04140c0c, 0x04141404, 0x04141414, 0x04141c0c, 0x04141c1c, 0x04141c3e,
-    0x04142c0c, 0x04142c3e, 0x04143e2c, 0x041c040c, 0x041c043e, 0x041c0c04, 0x041c0c14, 0x041c142c,
-    0x041c3e04, 0x04240c1c, 0x04241c3e, 0x04242424, 0x04242c3e, 0x04243e1c, 0x04243e2c, 0x042c040c,
-    0x042c043e, 0x042c1c14, 0x042c2c14, 0x04341c2c, 0x04343424, 0x043e0c04, 0x043e0c24, 0x043e0c34,
-    0x043e241c, 0x043e340c, 0x0c04040c, 0x0c04041c, 0x0c040c04, 0x0c040c14, 0x0c04140c, 0x0c04141c,
-    0x0c041c04, 0x0c041c14, 0x0c041c24, 0x0c04243e, 0x0c042c04, 0x0c0c0404, 0x0c0c0414, 0x0c0c0c0c,
-    0x0c0c1404, 0x0c0c1414, 0x0c14040c, 0x0c14041c, 0x0c140c04, 0x0c140c14, 0x0c14140c, 0x0c141c04,
-    0x0c143e14, 0x0c1c0404, 0x0c1c0414, 0x0c1c1404, 0x0c1c1c0c, 0x0c1c2434, 0x0c1c3434, 0x0c24040c,
-    0x0c24042c, 0x0c242c04, 0x0c2c1404, 0x0c2c1424, 0x0c2c2434, 0x0c2c3e0c, 0x0c34042c, 0x0c3e1414,
-    0x0c3e2404, 0x14040404, 0x14040414, 0x14040c0c, 0x14040c1c, 0x14041404, 0x14041414, 0x14041434,
-    0x14041c0c, 0x14042414, 0x140c040c, 0x140c041c, 0x140c042c, 0x140c0c04, 0x140c0c14, 0x140c140c,
-    0x140c1c04, 0x140c341c, 0x140c343e, 0x140c3e04, 0x14140404, 0x14140414, 0x14140c0c, 0x14140c3e,
-    0x14141404, 0x14141414, 0x14141c3e, 0x14142404, 0x14142c2c, 0x141c040c, 0x141c0c04, 0x141c0c24,
-    0x141c3e04, 0x141c3e24, 0x14241c2c, 0x14242c1c, 0x142c041c, 0x142c143e, 0x142c240c, 0x142c3e24,
-    0x143e040c, 0x143e041c, 0x143e0c34, 0x143e242c, 0x1c04040c, 0x1c040c04, 0x1c040c14, 0x1c04140c,
-    0x1c04141c, 0x1c042c04, 0x1c04342c, 0x1c043e14, 0x1c0c0404, 0x1c0c0414, 0x1c0c1404, 0x1c0c1c0c,
-    0x1c0c2424, 0x1c0c2434, 0x1c14040c, 0x1c14041c, 0x1c140c04, 0x1c14142c, 0x1c142c14, 0x1c143e14,
-    0x1c1c0c0c, 0x1c1c1c1c, 0x1c241c04, 0x1c24243e, 0x1c243e14, 0x1c2c0404, 0x1c2c0434, 0x1c2c1414,
-    0x1c2c2c2c, 0x1c340c24, 0x1c341c34, 0x1c34341c, 0x1c3e1c1c, 0x1c3e3404, 0x24040424, 0x24040c3e,
-    0x24041c2c, 0x24041c3e, 0x24042c1c, 0x24042c3e, 0x240c3e24, 0x24141404, 0x24141c3e, 0x24142404,
-    0x24143404, 0x24143434, 0x241c043e, 0x241c242c, 0x24240424, 0x24242c0c, 0x24243424, 0x242c142c,
-    0x242c241c, 0x242c3e04, 0x243e042c, 0x243e0c04, 0x243e0c14, 0x243e1c04, 0x2c040c14, 0x2c04240c,
-    0x2c043e04, 0x2c0c0404, 0x2c0c0434, 0x2c0c1434, 0x2c0c2c2c, 0x2c140c24, 0x2c141c14, 0x2c143e14,
-    0x2c1c0414, 0x2c1c2c1c, 0x2c240c04, 0x2c24141c, 0x2c24143e, 0x2c243e14, 0x2c2c0414, 0x2c2c1c0c,
-    0x2c342c04, 0x2c3e1424, 0x2c3e2414, 0x34041424, 0x34042424, 0x34042434, 0x34043424, 0x340c140c,
-    0x340c340c, 0x34140c3e, 0x34143424, 0x341c1c04, 0x341c1c34, 0x34242424, 0x342c042c, 0x342c2c14,
-    0x34341c1c, 0x343e041c, 0x343e140c, 0x3e04041c, 0x3e04042c, 0x3e04043e, 0x3e040c04, 0x3e041c14,
-    0x3e042c14, 0x3e0c1434, 0x3e0c2404, 0x3e140c14, 0x3e14242c, 0x3e142c14, 0x3e1c0404, 0x3e1c0c2c,
-    0x3e1c1c1c, 0x3e1c3404, 0x3e24140c, 0x3e24240c, 0x3e2c0404, 0x3e2c0414, 0x3e2c1424, 0x3e341c04,
-};
-
-static const __device__ uint32_t iq3s_grid[512] = {
-    0x01010101, 0x01010103, 0x01010105, 0x0101010b, 0x0101010f, 0x01010301, 0x01010303, 0x01010305,
-    0x01010309, 0x0101030d, 0x01010501, 0x01010503, 0x0101050b, 0x01010707, 0x01010901, 0x01010905,
-    0x0101090b, 0x0101090f, 0x01010b03, 0x01010b07, 0x01010d01, 0x01010d05, 0x01010f03, 0x01010f09,
-    0x01010f0f, 0x01030101, 0x01030103, 0x01030105, 0x01030109, 0x01030301, 0x01030303, 0x0103030b,
-    0x01030501, 0x01030507, 0x0103050f, 0x01030703, 0x0103070b, 0x01030909, 0x01030d03, 0x01030d0b,
-    0x01030f05, 0x01050101, 0x01050103, 0x0105010b, 0x0105010f, 0x01050301, 0x01050307, 0x0105030d,
-    0x01050503, 0x0105050b, 0x01050701, 0x01050709, 0x01050905, 0x0105090b, 0x0105090f, 0x01050b03,
-    0x01050b07, 0x01050f01, 0x01050f07, 0x01070107, 0x01070303, 0x0107030b, 0x01070501, 0x01070505,
-    0x01070703, 0x01070707, 0x0107070d, 0x01070909, 0x01070b01, 0x01070b05, 0x01070d0f, 0x01070f03,
-    0x01070f0b, 0x01090101, 0x01090307, 0x0109030f, 0x01090503, 0x01090509, 0x01090705, 0x01090901,
-    0x01090907, 0x01090b03, 0x01090f01, 0x010b0105, 0x010b0109, 0x010b0501, 0x010b0505, 0x010b050d,
-    0x010b0707, 0x010b0903, 0x010b090b, 0x010b090f, 0x010b0d0d, 0x010b0f07, 0x010d010d, 0x010d0303,
-    0x010d0307, 0x010d0703, 0x010d0b05, 0x010d0f03, 0x010f0101, 0x010f0105, 0x010f0109, 0x010f0501,
-    0x010f0505, 0x010f050d, 0x010f0707, 0x010f0b01, 0x010f0b09, 0x03010101, 0x03010103, 0x03010105,
-    0x03010109, 0x03010301, 0x03010303, 0x03010307, 0x0301030b, 0x0301030f, 0x03010501, 0x03010505,
-    0x03010703, 0x03010709, 0x0301070d, 0x03010b09, 0x03010b0d, 0x03010d03, 0x03010f05, 0x03030101,
-    0x03030103, 0x03030107, 0x0303010d, 0x03030301, 0x03030309, 0x03030503, 0x03030701, 0x03030707,
-    0x03030903, 0x03030b01, 0x03030b05, 0x03030f01, 0x03030f0d, 0x03050101, 0x03050305, 0x0305030b,
-    0x0305030f, 0x03050501, 0x03050509, 0x03050705, 0x03050901, 0x03050907, 0x03050b0b, 0x03050d01,
-    0x03050f05, 0x03070103, 0x03070109, 0x0307010f, 0x03070301, 0x03070307, 0x03070503, 0x0307050f,
-    0x03070701, 0x03070709, 0x03070903, 0x03070d05, 0x03070f01, 0x03090107, 0x0309010b, 0x03090305,
-    0x03090309, 0x03090703, 0x03090707, 0x03090905, 0x0309090d, 0x03090b01, 0x03090b09, 0x030b0103,
-    0x030b0301, 0x030b0307, 0x030b0503, 0x030b0701, 0x030b0705, 0x030b0b03, 0x030d0501, 0x030d0509,
-    0x030d050f, 0x030d0909, 0x030d090d, 0x030f0103, 0x030f0107, 0x030f0301, 0x030f0305, 0x030f0503,
-    0x030f070b, 0x030f0903, 0x030f0d05, 0x030f0f01, 0x05010101, 0x05010103, 0x05010107, 0x0501010b,
-    0x0501010f, 0x05010301, 0x05010305, 0x05010309, 0x0501030d, 0x05010503, 0x05010507, 0x0501050f,
-    0x05010701, 0x05010705, 0x05010903, 0x05010907, 0x0501090b, 0x05010b01, 0x05010b05, 0x05010d0f,
-    0x05010f01, 0x05010f07, 0x05010f0b, 0x05030101, 0x05030105, 0x05030301, 0x05030307, 0x0503030f,
-    0x05030505, 0x0503050b, 0x05030703, 0x05030709, 0x05030905, 0x05030b03, 0x05050103, 0x05050109,
-    0x0505010f, 0x05050503, 0x05050507, 0x05050701, 0x0505070f, 0x05050903, 0x05050b07, 0x05050b0f,
-    0x05050f03, 0x05050f09, 0x05070101, 0x05070105, 0x0507010b, 0x05070303, 0x05070505, 0x05070509,
-    0x05070703, 0x05070707, 0x05070905, 0x05070b01, 0x05070d0d, 0x05090103, 0x0509010f, 0x05090501,
-    0x05090507, 0x05090705, 0x0509070b, 0x05090903, 0x05090f05, 0x05090f0b, 0x050b0109, 0x050b0303,
-    0x050b0505, 0x050b070f, 0x050b0901, 0x050b0b07, 0x050b0f01, 0x050d0101, 0x050d0105, 0x050d010f,
-    0x050d0503, 0x050d0b0b, 0x050d0d03, 0x050f010b, 0x050f0303, 0x050f050d, 0x050f0701, 0x050f0907,
-    0x050f0b01, 0x07010105, 0x07010303, 0x07010307, 0x0701030b, 0x0701030f, 0x07010505, 0x07010703,
-    0x07010707, 0x0701070b, 0x07010905, 0x07010909, 0x0701090f, 0x07010b03, 0x07010d07, 0x07010f03,
-    0x07030103, 0x07030107, 0x0703010b, 0x07030309, 0x07030503, 0x07030507, 0x07030901, 0x07030d01,
-    0x07030f05, 0x07030f0d, 0x07050101, 0x07050305, 0x07050501, 0x07050705, 0x07050709, 0x07050b01,
-    0x07070103, 0x07070301, 0x07070309, 0x07070503, 0x07070507, 0x0707050f, 0x07070701, 0x07070903,
-    0x07070907, 0x0707090f, 0x07070b0b, 0x07070f07, 0x07090107, 0x07090303, 0x0709030d, 0x07090505,
-    0x07090703, 0x07090b05, 0x07090d01, 0x07090d09, 0x070b0103, 0x070b0301, 0x070b0305, 0x070b050b,
-    0x070b0705, 0x070b0909, 0x070b0b0d, 0x070b0f07, 0x070d030d, 0x070d0903, 0x070f0103, 0x070f0107,
-    0x070f0501, 0x070f0505, 0x070f070b, 0x09010101, 0x09010109, 0x09010305, 0x09010501, 0x09010509,
-    0x0901050f, 0x09010705, 0x09010903, 0x09010b01, 0x09010f01, 0x09030105, 0x0903010f, 0x09030303,
-    0x09030307, 0x09030505, 0x09030701, 0x0903070b, 0x09030907, 0x09030b03, 0x09030b0b, 0x09050103,
-    0x09050107, 0x09050301, 0x0905030b, 0x09050503, 0x09050707, 0x09050901, 0x09050b0f, 0x09050d05,
-    0x09050f01, 0x09070109, 0x09070303, 0x09070307, 0x09070501, 0x09070505, 0x09070703, 0x0907070b,
-    0x09090101, 0x09090105, 0x09090509, 0x0909070f, 0x09090901, 0x09090f03, 0x090b010b, 0x090b010f,
-    0x090b0503, 0x090b0d05, 0x090d0307, 0x090d0709, 0x090d0d01, 0x090f0301, 0x090f030b, 0x090f0701,
-    0x090f0907, 0x090f0b03, 0x0b010105, 0x0b010301, 0x0b010309, 0x0b010505, 0x0b010901, 0x0b010909,
-    0x0b01090f, 0x0b010b05, 0x0b010d0d, 0x0b010f09, 0x0b030103, 0x0b030107, 0x0b03010b, 0x0b030305,
-    0x0b030503, 0x0b030705, 0x0b030f05, 0x0b050101, 0x0b050303, 0x0b050507, 0x0b050701, 0x0b05070d,
-    0x0b050b07, 0x0b070105, 0x0b07010f, 0x0b070301, 0x0b07050f, 0x0b070909, 0x0b070b03, 0x0b070d0b,
-    0x0b070f07, 0x0b090103, 0x0b090109, 0x0b090501, 0x0b090705, 0x0b09090d, 0x0b0b0305, 0x0b0b050d,
-    0x0b0b0b03, 0x0b0b0b07, 0x0b0d0905, 0x0b0f0105, 0x0b0f0109, 0x0b0f0505, 0x0d010303, 0x0d010307,
-    0x0d01030b, 0x0d010703, 0x0d010707, 0x0d010d01, 0x0d030101, 0x0d030501, 0x0d03050f, 0x0d030d09,
-    0x0d050305, 0x0d050709, 0x0d050905, 0x0d050b0b, 0x0d050d05, 0x0d050f01, 0x0d070101, 0x0d070309,
-    0x0d070503, 0x0d070901, 0x0d09050b, 0x0d090907, 0x0d090d05, 0x0d0b0101, 0x0d0b0107, 0x0d0b0709,
-    0x0d0b0d01, 0x0d0d010b, 0x0d0d0901, 0x0d0f0303, 0x0d0f0307, 0x0f010101, 0x0f010109, 0x0f01010f,
-    0x0f010501, 0x0f010505, 0x0f01070d, 0x0f010901, 0x0f010b09, 0x0f010d05, 0x0f030105, 0x0f030303,
-    0x0f030509, 0x0f030907, 0x0f03090b, 0x0f050103, 0x0f050109, 0x0f050301, 0x0f05030d, 0x0f050503,
-    0x0f050701, 0x0f050b03, 0x0f070105, 0x0f070705, 0x0f07070b, 0x0f070b07, 0x0f090103, 0x0f09010b,
-    0x0f090307, 0x0f090501, 0x0f090b01, 0x0f0b0505, 0x0f0b0905, 0x0f0d0105, 0x0f0d0703, 0x0f0f0101,
-};
-
-static const __device__ uint64_t iq1s_grid[512] = {
-    0xffffffffffff0101, 0xffffffffff01ff00, 0xffffffffff010100, 0xffffffff00000000,
-    0xffffffff01ff00ff, 0xffffffff01ff0001, 0xffffffff0101ffff, 0xffffffff0101ff01,
-    0xffffff00ff000000, 0xffffff000000ff00, 0xffffff00000000ff, 0xffffff0000000100,
-    0xffffff0000010000, 0xffffff0001000000, 0xffffff01ffff00ff, 0xffffff01ff01ff00,
-    0xffffff01ff010100, 0xffffff0100000001, 0xffffff0101ffff00, 0xffffff0101ff0101,
-    0xffffff0101010100, 0xffff00ffff00ff01, 0xffff00ffff0000ff, 0xffff00ff00ff0100,
-    0xffff00ff0100ff00, 0xffff00ff010001ff, 0xffff0000ff0101ff, 0xffff000000ffff00,
-    0xffff000000000000, 0xffff00000001ff01, 0xffff000001000101, 0xffff0000010100ff,
-    0xffff0001ffff0100, 0xffff00010000ff00, 0xffff000100010101, 0xffff000101000000,
-    0xffff01ffffff0000, 0xffff01ffff01ffff, 0xffff01ffff010100, 0xffff01ff00000000,
-    0xffff01ff01ffffff, 0xffff01ff01ff0001, 0xffff01ff0101ffff, 0xffff01ff01010001,
-    0xffff0100ffffff01, 0xffff01000000ffff, 0xffff010000000100, 0xffff010001ff01ff,
-    0xffff010001000000, 0xffff0101ff000000, 0xffff0101000101ff, 0xffff010101ffff01,
-    0xffff01010101ff00, 0xff00ffffff000000, 0xff00ffff00ffff00, 0xff00ffff00000001,
-    0xff00ffff000001ff, 0xff00ffff01010000, 0xff00ff00ffff0000, 0xff00ff00ff00ff00,
-    0xff00ff00ff0000ff, 0xff00ff00ff000100, 0xff00ff00ff010001, 0xff00ff0000ff0001,
-    0xff00ff000000ffff, 0xff00ff0000000000, 0xff00ff000001ff00, 0xff00ff0000010100,
-    0xff00ff0001ff0000, 0xff00ff000100ff00, 0xff00ff0001000100, 0xff00ff01ff000000,
-    0xff00ff0100ff0000, 0xff00ff01000001ff, 0xff00ff0101010001, 0xff0000ff00000000,
-    0xff0000ff0001ff00, 0xff0000ff00010100, 0xff000000ffff0101, 0xff000000ff000000,
-    0xff000000ff01ff00, 0xff00000000ff0000, 0xff0000000000ff00, 0xff000000000000ff,
-    0xff00000000000000, 0xff00000000000001, 0xff00000000000100, 0xff0000000001ffff,
-    0xff00000000010000, 0xff00000001000000, 0xff00000001010100, 0xff000001ff00ff01,
-    0xff000001ff0100ff, 0xff00000100000000, 0xff0000010001ff00, 0xff00000101ff0100,
-    0xff0000010100ff00, 0xff0001ff00ff00ff, 0xff0001ff00000101, 0xff0001ff000100ff,
-    0xff0001ff01000000, 0xff000100ff0001ff, 0xff0001000000ff01, 0xff00010000000000,
-    0xff00010000010001, 0xff00010000010100, 0xff00010001ffff00, 0xff00010001ff0101,
-    0xff00010001010000, 0xff000101ffffffff, 0xff000101ff000101, 0xff00010101ff00ff,
-    0xff00010101000001, 0xff000101010100ff, 0xff01ffffff000101, 0xff01ffffff01ffff,
-    0xff01ffffff01ff01, 0xff01ffffff0101ff, 0xff01ffff00000000, 0xff01ffff01ff0001,
-    0xff01ffff0101ff01, 0xff01ff00ff000000, 0xff01ff0000ff0100, 0xff01ff000000ff01,
-    0xff01ff0000010000, 0xff01ff00010000ff, 0xff01ff01ff01ff00, 0xff01ff0100000101,
-    0xff0100ffffff0000, 0xff0100ffff010000, 0xff0100ff01ff00ff, 0xff0100ff01000100,
-    0xff0100ff010100ff, 0xff010000ffffff01, 0xff01000000000000, 0xff0100000101ff00,
-    0xff010001ffff00ff, 0xff010001ff000100, 0xff01000100ffff00, 0xff01000100010001,
-    0xff01000101ff0001, 0xff010001010001ff, 0xff0101ffffffffff, 0xff0101ffff01ffff,
-    0xff0101ffff010101, 0xff0101ff0000ff00, 0xff0101ff01010001, 0xff010100ff000000,
-    0xff010100ff01ff01, 0xff01010000ff0001, 0xff01010000000100, 0xff01010001000000,
-    0xff0101010100ffff, 0x00ffffff0000ff01, 0x00ffffff000000ff, 0x00ffffff00000100,
-    0x00ffffff00010000, 0x00ffff00ffff0001, 0x00ffff00ff0000ff, 0x00ffff00ff000100,
-    0x00ffff0000000000, 0x00ffff0001000100, 0x00ffff0001010001, 0x00ffff01ff00ff01,
-    0x00ffff0100ff0100, 0x00ffff010000ff00, 0x00ffff01000100ff, 0x00ffff0101ff00ff,
-    0x00ffff010101ff00, 0x00ff00ffffffffff, 0x00ff00ffffff01ff, 0x00ff00ffff000101,
-    0x00ff00ff00000000, 0x00ff00ff000101ff, 0x00ff00ff01010101, 0x00ff0000ff000000,
-    0x00ff0000ff01ffff, 0x00ff000000ff0000, 0x00ff00000000ff00, 0x00ff0000000000ff,
-    0x00ff000000000000, 0x00ff000000000001, 0x00ff000000000100, 0x00ff000000010000,
-    0x00ff000001ffff01, 0x00ff000001000000, 0x00ff0001ff000101, 0x00ff000100ffffff,
-    0x00ff000100000000, 0x00ff0001010001ff, 0x00ff01ffff000000, 0x00ff01ff0001ff00,
-    0x00ff01ff01ff0100, 0x00ff0100ff01ff01, 0x00ff010000ff00ff, 0x00ff010000ff0101,
-    0x00ff010000000000, 0x00ff010000010101, 0x00ff01000100ff00, 0x00ff010001010000,
-    0x00ff0101ffffff00, 0x00ff01010000ff01, 0x00ff010100000100, 0x00ff010101ff0000,
-    0x0000ffffffff0100, 0x0000ffffff00ff00, 0x0000ffffff0000ff, 0x0000ffffff010000,
-    0x0000ffff00000000, 0x0000ffff00010101, 0x0000ffff01ffff01, 0x0000ffff01000100,
-    0x0000ff00ff000000, 0x0000ff00ff01ff00, 0x0000ff00ff0101ff, 0x0000ff0000ff0000,
-    0x0000ff000000ff00, 0x0000ff00000000ff, 0x0000ff0000000000, 0x0000ff0000000001,
-    0x0000ff0000000100, 0x0000ff0000010000, 0x0000ff0001ffffff, 0x0000ff0001ff01ff,
-    0x0000ff0001000000, 0x0000ff000101ffff, 0x0000ff01ffff0101, 0x0000ff01ff010000,
-    0x0000ff0100000000, 0x0000ff0101000101, 0x000000ffffff0001, 0x000000ffff000000,
-    0x000000ff00ff0000, 0x000000ff0000ff00, 0x000000ff000000ff, 0x000000ff00000000,
-    0x000000ff00000001, 0x000000ff00000100, 0x000000ff00010000, 0x000000ff01000000,
-    0x000000ff0101ff00, 0x00000000ffff0000, 0x00000000ff00ff00, 0x00000000ff0000ff,
-    0x00000000ff000000, 0x00000000ff000001, 0x00000000ff000100, 0x00000000ff010000,
-    0x0000000000ffff00, 0x0000000000ff00ff, 0x0000000000ff0000, 0x0000000000ff0001,
-    0x0000000000ff0100, 0x000000000000ffff, 0x000000000000ff00, 0x000000000000ff01,
-    0x00000000000000ff, 0x0000000000000001, 0x00000000000001ff, 0x0000000000000100,
-    0x0000000000000101, 0x000000000001ff00, 0x00000000000100ff, 0x0000000000010000,
-    0x0000000000010001, 0x0000000000010100, 0x0000000001ff0000, 0x000000000100ff00,
-    0x00000000010000ff, 0x0000000001000000, 0x0000000001000001, 0x0000000001000100,
-    0x0000000001010000, 0x00000001ffff01ff, 0x00000001ff000000, 0x0000000100ff0000,
-    0x000000010000ff00, 0x00000001000000ff, 0x0000000100000000, 0x0000000100000001,
-    0x0000000100000100, 0x0000000100010000, 0x0000000101000000, 0x000001ffff00ff00,
-    0x000001ffff010001, 0x000001ffff0101ff, 0x000001ff00ffff01, 0x000001ff0000ffff,
-    0x000001ff00000000, 0x000001ff010000ff, 0x000001ff01010100, 0x00000100ffff0100,
-    0x00000100ff000000, 0x0000010000ff0000, 0x000001000000ff00, 0x00000100000000ff,
-    0x0000010000000000, 0x0000010000000001, 0x0000010000000100, 0x0000010000010000,
-    0x0000010001000000, 0x000001000101ff01, 0x00000101ffff0001, 0x00000101ff01ffff,
-    0x0000010100000000, 0x0000010101010100, 0x0001ffffff000000, 0x0001ffff00ffffff,
-    0x0001ffff00000100, 0x0001ffff0001ff00, 0x0001ffff01000000, 0x0001ff00ffffff00,
-    0x0001ff00ffff01ff, 0x0001ff00ff010000, 0x0001ff0000000000, 0x0001ff0000010001,
-    0x0001ff0001ff0000, 0x0001ff0001010100, 0x0001ff01ff0000ff, 0x0001ff01ff000001,
-    0x0001ff0100ffffff, 0x0001ff010001ffff, 0x0001ff01000101ff, 0x0001ff010100ff01,
-    0x000100ffff00ffff, 0x000100ffff00ff01, 0x000100ffff000100, 0x000100ff00000000,
-    0x000100ff000101ff, 0x000100ff01ff0101, 0x000100ff0100ffff, 0x000100ff01010101,
-    0x00010000ff000000, 0x00010000ff010100, 0x0001000000ff0000, 0x000100000000ff00,
-    0x00010000000000ff, 0x0001000000000000, 0x0001000000000001, 0x0001000000000100,
-    0x0001000000010000, 0x0001000001ffff01, 0x0001000001000000, 0x0001000100ff0101,
-    0x0001000100000000, 0x00010001010100ff, 0x000101ffffff01ff, 0x000101ffffff0101,
-    0x000101ff00010000, 0x000101ff01ff0000, 0x000101ff0100ff01, 0x00010100ffff0000,
-    0x0001010000000000, 0x000101000001ffff, 0x0001010000010101, 0x00010100010001ff,
-    0x00010101ff00ff00, 0x00010101ff010001, 0x0001010100ffffff, 0x0001010100ff01ff,
-    0x00010101000101ff, 0x0001010101ff0000, 0x000101010100ff01, 0x0001010101000101,
-    0x01ffffffffff0101, 0x01ffffffff01ffff, 0x01ffffffff01ff01, 0x01ffffffff0101ff,
-    0x01ffffffff010101, 0x01ffffff00000000, 0x01ffffff01ff01ff, 0x01ffffff01000101,
-    0x01ffffff0101ff01, 0x01ffffff010100ff, 0x01ffff000000ff00, 0x01ffff0000000001,
-    0x01ffff00000001ff, 0x01ffff0000010000, 0x01ffff0001ff0000, 0x01ffff01ffffffff,
-    0x01ffff01ffff01ff, 0x01ffff01ff000000, 0x01ffff01ff01ffff, 0x01ffff01ff0101ff,
-    0x01ffff010100ffff, 0x01ff00ffffff0000, 0x01ff00ffff010000, 0x01ff00ff00ffff01,
-    0x01ff0000ff0000ff, 0x01ff000000000000, 0x01ff00000001ff01, 0x01ff000001ffffff,
-    0x01ff000001010100, 0x01ff0001ffffff01, 0x01ff0001ff010001, 0x01ff000101ff0100,
-    0x01ff000101000001, 0x01ff0001010100ff, 0x01ff01ffff00ffff, 0x01ff01ff00010001,
-    0x01ff01ff01000000, 0x01ff01ff010101ff, 0x01ff0100ff000001, 0x01ff010000ffff00,
-    0x01ff010000000100, 0x01ff010001ff01ff, 0x01ff01000101ffff, 0x01ff0101ffff00ff,
-    0x01ff0101ffff0101, 0x01ff0101ff0101ff, 0x01ff010100010000, 0x0100ffff00ff00ff,
-    0x0100ffff00ff0001, 0x0100ffff00000100, 0x0100ffff0100ff00, 0x0100ff00ffff0000,
-    0x0100ff00ff00ffff, 0x0100ff00ff00ff01, 0x0100ff00ff000100, 0x0100ff00ff010000,
-    0x0100ff0000000000, 0x0100ff00000100ff, 0x0100ff0001ff0101, 0x0100ff0001010101,
-    0x0100ff0100ff00ff, 0x0100ff0100ff0001, 0x0100ff0100000100, 0x0100ff0100010001,
-    0x0100ff0101000000, 0x010000ffff00ff00, 0x010000ff0000ffff, 0x010000ff00000000,
-    0x010000ff010001ff, 0x010000ff01010001, 0x01000000ffffff00, 0x01000000ffff0101,
-    0x01000000ff000000, 0x01000000ff0100ff, 0x01000000ff010101, 0x0100000000ff0000,
-    0x010000000000ff00, 0x01000000000000ff, 0x0100000000000000, 0x0100000000000001,
-    0x0100000000000100, 0x0100000000010000, 0x0100000001000000, 0x0100000100000000,
-    0x01000001000101ff, 0x0100000101ffff01, 0x010001ffff000101, 0x010001ff00ff0100,
-    0x010001ff0000ff00, 0x010001ff000100ff, 0x010001ff01ffffff, 0x01000100ffff0000,
-    0x01000100ff0001ff, 0x0100010000000000, 0x010001000001ff00, 0x0100010001ff0000,
-    0x01000100010000ff, 0x0100010001000101, 0x01000101ff00ff01, 0x0100010100ff0100,
-    0x010001010000ffff, 0x0100010101010001, 0x0101ffffffff0101, 0x0101ffffff0001ff,
-    0x0101ffffff01ffff, 0x0101ffffff010101, 0x0101ffff00000000, 0x0101ffff0101ffff,
-    0x0101ffff010101ff, 0x0101ff00ff000000, 0x0101ff0000ff0100, 0x0101ff000000ff00,
-    0x0101ff0000010000, 0x0101ff00010000ff, 0x0101ff0001000001, 0x0101ff01ff010101,
-    0x0101ff0100000000, 0x0101ff010101ff00, 0x010100ffffff0000, 0x010100ffff010000,
-    0x010100ff00ff01ff, 0x010100ff000000ff, 0x010100ff00000101, 0x010100ff01ffff00,
-    0x01010000ffffff01, 0x01010000ff000100, 0x01010000ff01ff01, 0x0101000000000000,
-    0x01010000000100ff, 0x010100000101ff01, 0x01010001ffff0000, 0x01010001ff00ffff,
-    0x01010001ff010000, 0x0101000101ffffff, 0x0101000101ff01ff, 0x0101000101010101,
-    0x010101ffff01ffff, 0x010101ff00000000, 0x010101ff0001ff01, 0x010101ff0101ffff,
-    0x010101ff010101ff, 0x01010100ffffffff, 0x01010100ff000001, 0x010101000000ff00,
-    0x0101010001010000, 0x0101010100ff0001, 0x010101010001ff01, 0x010101010101ffff,
-};
-
-static const __device__ uint8_t ksigns_iq2xs[128] = {
-      0, 129, 130,   3, 132,   5,   6, 135, 136,   9,  10, 139,  12, 141, 142,  15,
-    144,  17,  18, 147,  20, 149, 150,  23,  24, 153, 154,  27, 156,  29,  30, 159,
-    160,  33,  34, 163,  36, 165, 166,  39,  40, 169, 170,  43, 172,  45,  46, 175,
-     48, 177, 178,  51, 180,  53,  54, 183, 184,  57,  58, 187,  60, 189, 190,  63,
-    192,  65,  66, 195,  68, 197, 198,  71,  72, 201, 202,  75, 204,  77,  78, 207,
-     80, 209, 210,  83, 212,  85,  86, 215, 216,  89,  90, 219,  92, 221, 222,  95,
-     96, 225, 226,  99, 228, 101, 102, 231, 232, 105, 106, 235, 108, 237, 238, 111,
-    240, 113, 114, 243, 116, 245, 246, 119, 120, 249, 250, 123, 252, 125, 126, 255,
-};
-
-//#if __CUDA_ARCH__ >= MIN_CC_DP4A // lowest compute capability for integer intrinsics
-static const __device__ uint64_t ksigns64[128] = {
-    0x0000000000000000, 0xff000000000000ff, 0xff0000000000ff00, 0x000000000000ffff,
-    0xff00000000ff0000, 0x0000000000ff00ff, 0x0000000000ffff00, 0xff00000000ffffff,
-    0xff000000ff000000, 0x00000000ff0000ff, 0x00000000ff00ff00, 0xff000000ff00ffff,
-    0x00000000ffff0000, 0xff000000ffff00ff, 0xff000000ffffff00, 0x00000000ffffffff,
-    0xff0000ff00000000, 0x000000ff000000ff, 0x000000ff0000ff00, 0xff0000ff0000ffff,
-    0x000000ff00ff0000, 0xff0000ff00ff00ff, 0xff0000ff00ffff00, 0x000000ff00ffffff,
-    0x000000ffff000000, 0xff0000ffff0000ff, 0xff0000ffff00ff00, 0x000000ffff00ffff,
-    0xff0000ffffff0000, 0x000000ffffff00ff, 0x000000ffffffff00, 0xff0000ffffffffff,
-    0xff00ff0000000000, 0x0000ff00000000ff, 0x0000ff000000ff00, 0xff00ff000000ffff,
-    0x0000ff0000ff0000, 0xff00ff0000ff00ff, 0xff00ff0000ffff00, 0x0000ff0000ffffff,
-    0x0000ff00ff000000, 0xff00ff00ff0000ff, 0xff00ff00ff00ff00, 0x0000ff00ff00ffff,
-    0xff00ff00ffff0000, 0x0000ff00ffff00ff, 0x0000ff00ffffff00, 0xff00ff00ffffffff,
-    0x0000ffff00000000, 0xff00ffff000000ff, 0xff00ffff0000ff00, 0x0000ffff0000ffff,
-    0xff00ffff00ff0000, 0x0000ffff00ff00ff, 0x0000ffff00ffff00, 0xff00ffff00ffffff,
-    0xff00ffffff000000, 0x0000ffffff0000ff, 0x0000ffffff00ff00, 0xff00ffffff00ffff,
-    0x0000ffffffff0000, 0xff00ffffffff00ff, 0xff00ffffffffff00, 0x0000ffffffffffff,
-    0xffff000000000000, 0x00ff0000000000ff, 0x00ff00000000ff00, 0xffff00000000ffff,
-    0x00ff000000ff0000, 0xffff000000ff00ff, 0xffff000000ffff00, 0x00ff000000ffffff,
-    0x00ff0000ff000000, 0xffff0000ff0000ff, 0xffff0000ff00ff00, 0x00ff0000ff00ffff,
-    0xffff0000ffff0000, 0x00ff0000ffff00ff, 0x00ff0000ffffff00, 0xffff0000ffffffff,
-    0x00ff00ff00000000, 0xffff00ff000000ff, 0xffff00ff0000ff00, 0x00ff00ff0000ffff,
-    0xffff00ff00ff0000, 0x00ff00ff00ff00ff, 0x00ff00ff00ffff00, 0xffff00ff00ffffff,
-    0xffff00ffff000000, 0x00ff00ffff0000ff, 0x00ff00ffff00ff00, 0xffff00ffff00ffff,
-    0x00ff00ffffff0000, 0xffff00ffffff00ff, 0xffff00ffffffff00, 0x00ff00ffffffffff,
-    0x00ffff0000000000, 0xffffff00000000ff, 0xffffff000000ff00, 0x00ffff000000ffff,
-    0xffffff0000ff0000, 0x00ffff0000ff00ff, 0x00ffff0000ffff00, 0xffffff0000ffffff,
-    0xffffff00ff000000, 0x00ffff00ff0000ff, 0x00ffff00ff00ff00, 0xffffff00ff00ffff,
-    0x00ffff00ffff0000, 0xffffff00ffff00ff, 0xffffff00ffffff00, 0x00ffff00ffffffff,
-    0xffffffff00000000, 0x00ffffff000000ff, 0x00ffffff0000ff00, 0xffffffff0000ffff,
-    0x00ffffff00ff0000, 0xffffffff00ff00ff, 0xffffffff00ffff00, 0x00ffffff00ffffff,
-    0x00ffffffff000000, 0xffffffffff0000ff, 0xffffffffff00ff00, 0x00ffffffff00ffff,
-    0xffffffffffff0000, 0x00ffffffffff00ff, 0x00ffffffffffff00, 0xffffffffffffffff,
-};
-//#endif
-
-static const __device__ uint8_t kmask_iq2xs[8] = {1, 2, 4, 8, 16, 32, 64, 128};
-
 inline bool ggml_cuda_supports_mmq(enum ggml_type type) {
     switch (type) {
         case GGML_TYPE_Q4_0:
@@ -2460,11 +1723,22 @@ static __global__ void dequantize_block_iq1_s(const void * __restrict__ vx, dst_
     const int il = tid/8; // 0...3
     const int ib = tid%8; // 0...7
     dst_t * y = yy + i*QK_K + 32*ib + 8*il;
-    const int i8 = 4*ib+il;
-    uint8_t h = x[i].scales[i8/2] >> 4*(i8%2);
-    const int8_t * grid = (const int8_t *)(iq1s_grid + (x[i].qs[i8] | ((h & 8) << 5)));
-    const float d = (float)x[i].d * (2*(h & 7) + 1);
-    for (int j = 0; j < 8; ++j) y[j] = d * grid[j];
+    const float d = (float)x[i].d * (2*((x[i].qh[ib] >> 12) & 0xf) + 1);
+#if __CUDA_ARCH__ >= MIN_CC_DP4A // lowest compute capability for integer intrinsics
+    int grid32[2]; const int8_t * q = (const int8_t *)grid32;
+    grid32[0] = *((const int *)(iq1s_grid_gpu + (x[i].qs[4*ib+il] | (((x[i].qh[ib] >> 3*il) & 7) << 8))));
+    grid32[1] = __vsub4((grid32[0] >>  4) & 0x0f0f0f0f, 0x01010101);
+    grid32[0] = __vsub4(grid32[0] & 0x0f0f0f0f, 0x01010101);
+    for (int j = 0; j < 8; ++j) {
+        y[j] = d * q[j];
+    }
+#else
+    const uint8_t * grid = (const uint8_t *)(iq1s_grid_gpu + (x[i].qs[4*ib+il] | (((x[i].qh[ib] >> 3*il) & 7) << 8)));
+    for (int j = 0; j < 4; ++j) {
+        y[j+0] = d * ((grid[j] & 0xf) - 1);
+        y[j+4] = d * ((grid[j] >>  4) - 1);
+    }
+#endif
 #else
     assert(false);
 #endif
@@ -5276,44 +4550,33 @@ static __device__ __forceinline__ float vec_dot_iq3_s_q8_1(
 #endif
 }
 
-
 static __device__ __forceinline__ float vec_dot_iq1_s_q8_1(
     const void * __restrict__ vbq, const block_q8_1 * __restrict__ bq8_1, const int & iqs) {
 #if QK_K == 256
     const block_iq1_s * bq1 = (const block_iq1_s *) vbq;
 
     const int ib32 = iqs;
-    int sumi1 = 0, sumi2 = 0, sumi3 = 0, sumi4 = 0;
-    const uint8_t h1 = bq1->scales[2*ib32+0];
-    const uint8_t h2 = bq1->scales[2*ib32+1];
+    int sumi = 0;
 #if __CUDA_ARCH__ >= MIN_CC_DP4A // lowest compute capability for integer intrinsics
     const int * q8 = (const int *)bq8_1[ib32].qs;
-    const int * grid1 = (const int *)(iq1s_grid + (bq1->qs[4*ib32+0] | ((h1 & 0x08) << 5)));
-    const int * grid2 = (const int *)(iq1s_grid + (bq1->qs[4*ib32+1] | ((h1 & 0x80) << 1)));
-    const int * grid3 = (const int *)(iq1s_grid + (bq1->qs[4*ib32+2] | ((h2 & 0x08) << 5)));
-    const int * grid4 = (const int *)(iq1s_grid + (bq1->qs[4*ib32+3] | ((h2 & 0x80) << 1)));
-    for (int j = 0; j < 2; ++j) {
-        sumi1 = __dp4a(q8[j+0], grid1[j], sumi1);
-        sumi2 = __dp4a(q8[j+2], grid2[j], sumi2);
-        sumi3 = __dp4a(q8[j+4], grid3[j], sumi3);
-        sumi4 = __dp4a(q8[j+6], grid4[j], sumi4);
+    for (int l = 0; l < 4; ++l) {
+        const int * grid = (const int *)(iq1s_grid_gpu + (bq1->qs[4*ib32+l] | (((bq1->qh[ib32] >> 3*l) & 7) << 8)));
+        int grid0 = __vsub4(grid[0] & 0x0f0f0f0f, 0x01010101);
+        int grid1 = __vsub4((grid[0] >> 4) & 0x0f0f0f0f, 0x01010101);
+        sumi = __dp4a(q8[2*l+1], grid1, __dp4a(q8[2*l+0], grid0, sumi));
     }
 #else
     const int8_t   * q8 = bq8_1[ib32].qs;
-    const int8_t * grid1 = (const int8_t *)(iq1s_grid + (bq1->qs[4*ib32+0] | ((h1 & 0x08) << 5)));
-    const int8_t * grid2 = (const int8_t *)(iq1s_grid + (bq1->qs[4*ib32+1] | ((h1 & 0x80) << 1)));
-    const int8_t * grid3 = (const int8_t *)(iq1s_grid + (bq1->qs[4*ib32+2] | ((h2 & 0x08) << 5)));
-    const int8_t * grid4 = (const int8_t *)(iq1s_grid + (bq1->qs[4*ib32+3] | ((h2 & 0x80) << 1)));
-    for (int j = 0; j < 8; ++j) {
-        sumi1 += q8[j+ 0] * grid1[j];
-        sumi2 += q8[j+ 8] * grid2[j];
-        sumi3 += q8[j+16] * grid3[j];
-        sumi4 += q8[j+24] * grid4[j];
+    for (int l = 0; l < 4; ++l) {
+        const uint8_t * grid = (const uint8_t *)(iq1s_grid_gpu + (bq1->qs[4*ib32+l] | (((bq1->qh[ib32] >> 3*l) & 7) << 8)));
+        for (int j = 0; j < 4; ++j) {
+            sumi += q8[j] * ((grid[j] & 0xf) - 1) + q8[j+4] * ((grid[j] >>  4) - 1);
+        }
+        q8 += 8;
     }
 #endif
     const float d = (float)bq1->d * __low2float(bq8_1[ib32].ds);
-    return d * (sumi1 * (2*(h1 & 7) + 1) + sumi2 * (2*((h1 >> 4) & 7) + 1) +
-                sumi3 * (2*(h2 & 7) + 1) + sumi4 * (2*((h2 >> 4) & 7) + 1));
+    return d * sumi * (2*(bq1->qh[ib32] >> 12) + 1);
 #else
     assert(false);
     return 0.f;
diff --git a/ggml-impl.h b/ggml-impl.h
index c5637e4d4..e68b72877 100644
--- a/ggml-impl.h
+++ b/ggml-impl.h
@@ -53,26 +53,30 @@ extern "C" {
 //
 #include <arm_neon.h>
 
+typedef __fp16 ggml_fp16_internal_t;
+
 #define GGML_COMPUTE_FP16_TO_FP32(x) ggml_compute_fp16_to_fp32(x)
 #define GGML_COMPUTE_FP32_TO_FP16(x) ggml_compute_fp32_to_fp16(x)
 
 #define GGML_FP16_TO_FP32(x) ggml_compute_fp16_to_fp32(x)
 
 static inline float ggml_compute_fp16_to_fp32(ggml_fp16_t h) {
-    __fp16 tmp;
+    ggml_fp16_internal_t tmp;
     memcpy(&tmp, &h, sizeof(ggml_fp16_t));
     return (float)tmp;
 }
 
 static inline ggml_fp16_t ggml_compute_fp32_to_fp16(float f) {
     ggml_fp16_t res;
-    __fp16 tmp = f;
+    ggml_fp16_internal_t tmp = f;
     memcpy(&res, &tmp, sizeof(ggml_fp16_t));
     return res;
 }
 
 #else
 
+typedef uint16_t ggml_fp16_internal_t;
+
 #ifdef __wasm_simd128__
 #include <wasm_simd128.h>
 #else
diff --git a/ggml-metal.m b/ggml-metal.m
index 00df22838..3cf80de7b 100644
--- a/ggml-metal.m
+++ b/ggml-metal.m
@@ -1642,8 +1642,8 @@ static enum ggml_status ggml_metal_graph_compute(
                         // TODO: make this more general
                         GGML_ASSERT(n_as <= 8);
 
-                        // max size of the src1ids array in the kernel stack
-                        GGML_ASSERT(ne11 <= 512);
+                        // max size of the src1ids array in the kernel shared buffer
+                        GGML_ASSERT(ne11 <= 4096);
 
                         const int64_t  ne20 = src2 ? src2->ne[0] : 0;
                         const int64_t  ne21 = src2 ? src2->ne[1] : 0;
@@ -1741,7 +1741,7 @@ static enum ggml_status ggml_metal_graph_compute(
                                 [encoder setBuffer:id_src_cur offset:offs_src_cur atIndex:19 + j];
                             }
 
-                            [encoder setThreadgroupMemoryLength:8192 atIndex:0];
+                            [encoder setThreadgroupMemoryLength:GGML_PAD(8192 + 2*ne11, 16) atIndex:0];
 
                             [encoder dispatchThreadgroups:MTLSizeMake((ne11 + 31)/32, (ne21 + 63)/64, n_as*ne12*ne13) threadsPerThreadgroup:MTLSizeMake(128, 1, 1)];
                         } else {
diff --git a/ggml-metal.metal b/ggml-metal.metal
index a65d12641..912822ee6 100644
--- a/ggml-metal.metal
+++ b/ggml-metal.metal
@@ -1,5 +1,8 @@
 #include <metal_stdlib>
 
+#define GGML_COMMON_IMPL_METAL
+#include "ggml-common.h"
+
 using namespace metal;
 
 #define MAX(x, y) ((x) > (y) ? (x) : (y))
@@ -2592,8 +2595,8 @@ typedef struct {
 
 typedef struct {
     half d;
-    uint8_t qs[QK_K/8];
-    uint8_t scales[QK_K/16];
+    uint8_t  qs[QK_K/8];
+    uint16_t qh[QK_K/32];
 } block_iq1_s;
 
 // Non-linear quants
@@ -3638,710 +3641,6 @@ kernel void kernel_mul_mv_q6_K_f32(
 
 // ======================= "True" 2-bit
 
-constexpr constant static uint64_t iq2xxs_grid[256] = {
-    0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08,
-    0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x08080808082b0808,
-    0x08080808082b082b, 0x08080808082b2b08, 0x08080808082b2b2b, 0x0808080819080819,
-    0x0808080819081908, 0x0808080819190808, 0x0808080819192b08, 0x08080808192b0819,
-    0x08080808192b1908, 0x080808082b080808, 0x080808082b08082b, 0x080808082b082b2b,
-    0x080808082b2b082b, 0x0808081908080819, 0x0808081908081908, 0x0808081908190808,
-    0x0808081908191919, 0x0808081919080808, 0x080808192b081908, 0x080808192b192b08,
-    0x0808082b08080808, 0x0808082b0808082b, 0x0808082b082b082b, 0x0808082b2b08082b,
-    0x0808190808080819, 0x0808190808081908, 0x0808190808190808, 0x08081908082b0819,
-    0x08081908082b1908, 0x0808190819080808, 0x080819081908082b, 0x0808190819082b08,
-    0x08081908192b0808, 0x080819082b080819, 0x080819082b081908, 0x080819082b190808,
-    0x080819082b2b1908, 0x0808191908080808, 0x080819190808082b, 0x0808191908082b08,
-    0x08081919082b0808, 0x080819191908192b, 0x08081919192b2b19, 0x080819192b080808,
-    0x080819192b190819, 0x0808192b08082b19, 0x0808192b08190808, 0x0808192b19080808,
-    0x0808192b2b081908, 0x0808192b2b2b1908, 0x08082b0808080808, 0x08082b0808081919,
-    0x08082b0808082b08, 0x08082b0808191908, 0x08082b08082b2b08, 0x08082b0819080819,
-    0x08082b0819081908, 0x08082b0819190808, 0x08082b081919082b, 0x08082b082b082b08,
-    0x08082b1908081908, 0x08082b1919080808, 0x08082b2b0808082b, 0x08082b2b08191908,
-    0x0819080808080819, 0x0819080808081908, 0x0819080808190808, 0x08190808082b0819,
-    0x0819080819080808, 0x08190808192b0808, 0x081908082b081908, 0x081908082b190808,
-    0x081908082b191919, 0x0819081908080808, 0x0819081908082b08, 0x08190819082b0808,
-    0x0819081919190808, 0x0819081919192b2b, 0x081908192b080808, 0x0819082b082b1908,
-    0x0819082b19081919, 0x0819190808080808, 0x0819190808082b08, 0x08191908082b0808,
-    0x08191908082b1919, 0x0819190819082b19, 0x081919082b080808, 0x0819191908192b08,
-    0x08191919192b082b, 0x0819192b08080808, 0x0819192b0819192b, 0x08192b0808080819,
-    0x08192b0808081908, 0x08192b0808190808, 0x08192b0819080808, 0x08192b082b080819,
-    0x08192b1908080808, 0x08192b1908081919, 0x08192b192b2b0808, 0x08192b2b19190819,
-    0x082b080808080808, 0x082b08080808082b, 0x082b080808082b2b, 0x082b080819081908,
-    0x082b0808192b0819, 0x082b08082b080808, 0x082b08082b08082b, 0x082b0819082b2b19,
-    0x082b081919082b08, 0x082b082b08080808, 0x082b082b0808082b, 0x082b190808080819,
-    0x082b190808081908, 0x082b190808190808, 0x082b190819080808, 0x082b19081919192b,
-    0x082b191908080808, 0x082b191919080819, 0x082b1919192b1908, 0x082b192b2b190808,
-    0x082b2b0808082b08, 0x082b2b08082b0808, 0x082b2b082b191908, 0x082b2b2b19081908,
-    0x1908080808080819, 0x1908080808081908, 0x1908080808190808, 0x1908080808192b08,
-    0x19080808082b0819, 0x19080808082b1908, 0x1908080819080808, 0x1908080819082b08,
-    0x190808081919192b, 0x19080808192b0808, 0x190808082b080819, 0x190808082b081908,
-    0x190808082b190808, 0x1908081908080808, 0x19080819082b0808, 0x19080819192b0819,
-    0x190808192b080808, 0x190808192b081919, 0x1908082b08080819, 0x1908082b08190808,
-    0x1908082b19082b08, 0x1908082b1919192b, 0x1908082b192b2b08, 0x1908190808080808,
-    0x1908190808082b08, 0x19081908082b0808, 0x190819082b080808, 0x190819082b192b19,
-    0x190819190819082b, 0x19081919082b1908, 0x1908192b08080808, 0x19082b0808080819,
-    0x19082b0808081908, 0x19082b0808190808, 0x19082b0819080808, 0x19082b0819081919,
-    0x19082b1908080808, 0x19082b1919192b08, 0x19082b19192b0819, 0x19082b192b08082b,
-    0x19082b2b19081919, 0x19082b2b2b190808, 0x1919080808080808, 0x1919080808082b08,
-    0x1919080808190819, 0x1919080808192b19, 0x19190808082b0808, 0x191908082b080808,
-    0x191908082b082b08, 0x1919081908081908, 0x191908191908082b, 0x191908192b2b1908,
-    0x1919082b2b190819, 0x191919082b190808, 0x191919082b19082b, 0x1919191908082b2b,
-    0x1919192b08080819, 0x1919192b19191908, 0x19192b0808080808, 0x19192b0808190819,
-    0x19192b0808192b19, 0x19192b08192b1908, 0x19192b1919080808, 0x19192b2b08082b08,
-    0x192b080808081908, 0x192b080808190808, 0x192b080819080808, 0x192b0808192b2b08,
-    0x192b081908080808, 0x192b081919191919, 0x192b082b08192b08, 0x192b082b192b0808,
-    0x192b190808080808, 0x192b190808081919, 0x192b191908190808, 0x192b19190819082b,
-    0x192b19192b081908, 0x192b2b081908082b, 0x2b08080808080808, 0x2b0808080808082b,
-    0x2b08080808082b2b, 0x2b08080819080819, 0x2b0808082b08082b, 0x2b08081908081908,
-    0x2b08081908192b08, 0x2b08081919080808, 0x2b08082b08190819, 0x2b08190808080819,
-    0x2b08190808081908, 0x2b08190808190808, 0x2b08190808191919, 0x2b08190819080808,
-    0x2b081908192b0808, 0x2b08191908080808, 0x2b0819191908192b, 0x2b0819192b191908,
-    0x2b08192b08082b19, 0x2b08192b19080808, 0x2b08192b192b0808, 0x2b082b080808082b,
-    0x2b082b1908081908, 0x2b082b2b08190819, 0x2b19080808081908, 0x2b19080808190808,
-    0x2b190808082b1908, 0x2b19080819080808, 0x2b1908082b2b0819, 0x2b1908190819192b,
-    0x2b1908192b080808, 0x2b19082b19081919, 0x2b19190808080808, 0x2b191908082b082b,
-    0x2b19190819081908, 0x2b19191919190819, 0x2b192b082b080819, 0x2b192b19082b0808,
-    0x2b2b08080808082b, 0x2b2b080819190808, 0x2b2b08082b081919, 0x2b2b081908082b19,
-    0x2b2b082b08080808, 0x2b2b190808192b08, 0x2b2b2b0819190808, 0x2b2b2b1908081908,
-};
-
-constexpr constant static uint64_t iq2xs_grid[512] = {
-    0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08,
-    0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x080808080819192b,
-    0x0808080808192b19, 0x08080808082b0808, 0x08080808082b082b, 0x08080808082b1919,
-    0x08080808082b2b08, 0x0808080819080819, 0x0808080819081908, 0x080808081908192b,
-    0x0808080819082b19, 0x0808080819190808, 0x080808081919082b, 0x0808080819191919,
-    0x0808080819192b08, 0x08080808192b0819, 0x08080808192b1908, 0x080808082b080808,
-    0x080808082b08082b, 0x080808082b081919, 0x080808082b082b08, 0x080808082b190819,
-    0x080808082b191908, 0x080808082b192b19, 0x080808082b2b0808, 0x0808081908080819,
-    0x0808081908081908, 0x080808190808192b, 0x0808081908082b19, 0x0808081908190808,
-    0x080808190819082b, 0x0808081908191919, 0x0808081908192b08, 0x0808081908192b2b,
-    0x08080819082b0819, 0x08080819082b1908, 0x0808081919080808, 0x080808191908082b,
-    0x0808081919081919, 0x0808081919082b08, 0x0808081919190819, 0x0808081919191908,
-    0x08080819192b0808, 0x08080819192b2b08, 0x080808192b080819, 0x080808192b081908,
-    0x080808192b190808, 0x0808082b08080808, 0x0808082b0808082b, 0x0808082b08081919,
-    0x0808082b08082b08, 0x0808082b08190819, 0x0808082b08191908, 0x0808082b082b0808,
-    0x0808082b19080819, 0x0808082b19081908, 0x0808082b19190808, 0x0808082b19191919,
-    0x0808082b2b080808, 0x0808082b2b082b2b, 0x0808190808080819, 0x0808190808081908,
-    0x080819080808192b, 0x0808190808082b19, 0x0808190808190808, 0x080819080819082b,
-    0x0808190808191919, 0x0808190808192b08, 0x08081908082b0819, 0x08081908082b1908,
-    0x0808190819080808, 0x080819081908082b, 0x0808190819081919, 0x0808190819082b08,
-    0x0808190819190819, 0x0808190819191908, 0x080819081919192b, 0x08081908192b0808,
-    0x080819082b080819, 0x080819082b081908, 0x080819082b190808, 0x0808191908080808,
-    0x080819190808082b, 0x0808191908081919, 0x0808191908082b08, 0x0808191908190819,
-    0x0808191908191908, 0x08081919082b0808, 0x0808191919080819, 0x0808191919081908,
-    0x0808191919190808, 0x08081919192b0819, 0x080819192b080808, 0x0808192b08080819,
-    0x0808192b08081908, 0x0808192b08190808, 0x0808192b082b192b, 0x0808192b19080808,
-    0x0808192b1908082b, 0x0808192b2b081908, 0x08082b0808080808, 0x08082b080808082b,
-    0x08082b0808081919, 0x08082b0808082b08, 0x08082b0808082b2b, 0x08082b0808190819,
-    0x08082b0808191908, 0x08082b08082b0808, 0x08082b08082b1919, 0x08082b0819080819,
-    0x08082b0819081908, 0x08082b0819190808, 0x08082b0819192b08, 0x08082b082b080808,
-    0x08082b082b2b0808, 0x08082b082b2b2b2b, 0x08082b1908080819, 0x08082b1908081908,
-    0x08082b1908190808, 0x08082b1919080808, 0x08082b192b080819, 0x08082b192b082b19,
-    0x08082b2b08080808, 0x08082b2b082b0808, 0x08082b2b082b2b08, 0x08082b2b2b19192b,
-    0x08082b2b2b2b0808, 0x0819080808080819, 0x0819080808081908, 0x081908080808192b,
-    0x0819080808082b19, 0x0819080808190808, 0x081908080819082b, 0x0819080808191919,
-    0x0819080808192b08, 0x08190808082b0819, 0x08190808082b1908, 0x0819080819080808,
-    0x081908081908082b, 0x0819080819081919, 0x0819080819082b08, 0x0819080819190819,
-    0x0819080819191908, 0x08190808192b0808, 0x08190808192b2b2b, 0x081908082b080819,
-    0x081908082b081908, 0x081908082b190808, 0x0819081908080808, 0x081908190808082b,
-    0x0819081908081919, 0x0819081908082b08, 0x0819081908190819, 0x0819081908191908,
-    0x08190819082b0808, 0x0819081919080819, 0x0819081919081908, 0x0819081919190808,
-    0x081908192b080808, 0x081908192b191908, 0x081908192b19192b, 0x0819082b08080819,
-    0x0819082b08081908, 0x0819082b0808192b, 0x0819082b08190808, 0x0819082b19080808,
-    0x0819082b192b0808, 0x0819190808080808, 0x081919080808082b, 0x0819190808081919,
-    0x0819190808082b08, 0x0819190808190819, 0x0819190808191908, 0x08191908082b0808,
-    0x0819190819080819, 0x0819190819081908, 0x0819190819082b19, 0x0819190819190808,
-    0x08191908192b1908, 0x081919082b080808, 0x0819191908080819, 0x0819191908081908,
-    0x0819191908190808, 0x0819191919080808, 0x0819192b08080808, 0x0819192b08191908,
-    0x0819192b19082b19, 0x08192b0808080819, 0x08192b0808081908, 0x08192b0808190808,
-    0x08192b080819082b, 0x08192b0819080808, 0x08192b0819191908, 0x08192b082b08192b,
-    0x08192b1908080808, 0x08192b1908081919, 0x08192b19192b192b, 0x08192b2b19190819,
-    0x08192b2b2b2b2b19, 0x082b080808080808, 0x082b08080808082b, 0x082b080808081919,
-    0x082b080808082b08, 0x082b080808082b2b, 0x082b080808190819, 0x082b080808191908,
-    0x082b0808082b0808, 0x082b080819080819, 0x082b080819081908, 0x082b080819190808,
-    0x082b08082b080808, 0x082b08082b2b0808, 0x082b081908080819, 0x082b081908081908,
-    0x082b081908190808, 0x082b081919080808, 0x082b081919082b08, 0x082b0819192b1919,
-    0x082b082b08080808, 0x082b082b082b082b, 0x082b082b2b080808, 0x082b082b2b2b2b08,
-    0x082b190808080819, 0x082b190808081908, 0x082b190808190808, 0x082b1908082b2b19,
-    0x082b190819080808, 0x082b191908080808, 0x082b191919080819, 0x082b19191919082b,
-    0x082b19192b192b19, 0x082b192b08080819, 0x082b192b08192b2b, 0x082b192b2b2b192b,
-    0x082b2b0808080808, 0x082b2b0808082b08, 0x082b2b0808082b2b, 0x082b2b08082b0808,
-    0x082b2b0819191919, 0x082b2b082b082b08, 0x082b2b082b2b082b, 0x082b2b19192b2b08,
-    0x082b2b192b190808, 0x082b2b2b08082b08, 0x082b2b2b082b0808, 0x082b2b2b2b08082b,
-    0x082b2b2b2b082b08, 0x082b2b2b2b082b2b, 0x1908080808080819, 0x1908080808081908,
-    0x190808080808192b, 0x1908080808082b19, 0x1908080808190808, 0x190808080819082b,
-    0x1908080808191919, 0x1908080808192b08, 0x19080808082b0819, 0x19080808082b1908,
-    0x1908080819080808, 0x190808081908082b, 0x1908080819081919, 0x1908080819082b08,
-    0x1908080819082b2b, 0x1908080819190819, 0x1908080819191908, 0x19080808192b0808,
-    0x19080808192b1919, 0x190808082b080819, 0x190808082b081908, 0x190808082b190808,
-    0x1908081908080808, 0x190808190808082b, 0x1908081908081919, 0x1908081908082b08,
-    0x1908081908190819, 0x1908081908191908, 0x19080819082b0808, 0x1908081919080819,
-    0x1908081919081908, 0x1908081919190808, 0x190808192b080808, 0x190808192b081919,
-    0x190808192b2b082b, 0x1908082b08080819, 0x1908082b08081908, 0x1908082b08190808,
-    0x1908082b0819082b, 0x1908082b082b2b19, 0x1908082b19080808, 0x1908190808080808,
-    0x190819080808082b, 0x1908190808081919, 0x1908190808082b08, 0x1908190808190819,
-    0x1908190808191908, 0x1908190808192b19, 0x19081908082b0808, 0x1908190819080819,
-    0x1908190819081908, 0x1908190819190808, 0x190819082b080808, 0x190819082b191908,
-    0x1908191908080819, 0x1908191908081908, 0x1908191908190808, 0x19081919082b1908,
-    0x1908191919080808, 0x190819192b192b2b, 0x1908192b08080808, 0x1908192b08082b2b,
-    0x1908192b19081908, 0x1908192b19190808, 0x19082b0808080819, 0x19082b0808081908,
-    0x19082b0808190808, 0x19082b0819080808, 0x19082b0819081919, 0x19082b0819191908,
-    0x19082b08192b082b, 0x19082b1908080808, 0x19082b1908190819, 0x19082b1919081908,
-    0x19082b1919190808, 0x19082b19192b2b19, 0x19082b2b08081908, 0x1919080808080808,
-    0x191908080808082b, 0x1919080808081919, 0x1919080808082b08, 0x1919080808190819,
-    0x1919080808191908, 0x19190808082b0808, 0x19190808082b2b08, 0x1919080819080819,
-    0x1919080819081908, 0x1919080819190808, 0x191908082b080808, 0x1919081908080819,
-    0x1919081908081908, 0x1919081908190808, 0x1919081908191919, 0x1919081919080808,
-    0x191908191908082b, 0x1919082b08080808, 0x1919082b19081908, 0x1919082b2b2b2b2b,
-    0x1919190808080819, 0x1919190808081908, 0x1919190808190808, 0x19191908082b0819,
-    0x1919190819080808, 0x19191908192b0808, 0x191919082b080819, 0x191919082b2b0819,
-    0x1919191908080808, 0x1919191908082b08, 0x191919192b080808, 0x191919192b082b08,
-    0x1919192b082b0819, 0x1919192b192b2b08, 0x1919192b2b2b0819, 0x19192b0808080808,
-    0x19192b0808191908, 0x19192b0819080819, 0x19192b0819190808, 0x19192b082b192b19,
-    0x19192b1908192b2b, 0x19192b1919080808, 0x19192b191908082b, 0x19192b2b2b081919,
-    0x192b080808080819, 0x192b080808081908, 0x192b080808190808, 0x192b080819080808,
-    0x192b080819191908, 0x192b0808192b082b, 0x192b08082b08192b, 0x192b08082b2b2b19,
-    0x192b081908080808, 0x192b082b082b1908, 0x192b082b19082b2b, 0x192b082b2b19082b,
-    0x192b190808080808, 0x192b19080819192b, 0x192b191908190808, 0x192b191919080808,
-    0x192b191919081919, 0x192b19192b2b1908, 0x192b2b0808080819, 0x192b2b08192b2b2b,
-    0x192b2b19082b1919, 0x192b2b2b0808192b, 0x192b2b2b19191908, 0x192b2b2b192b082b,
-    0x2b08080808080808, 0x2b0808080808082b, 0x2b08080808081919, 0x2b08080808082b08,
-    0x2b08080808190819, 0x2b08080808191908, 0x2b080808082b0808, 0x2b080808082b2b2b,
-    0x2b08080819080819, 0x2b08080819081908, 0x2b08080819190808, 0x2b0808082b080808,
-    0x2b0808082b08082b, 0x2b0808082b2b2b08, 0x2b0808082b2b2b2b, 0x2b08081908080819,
-    0x2b08081908081908, 0x2b0808190808192b, 0x2b08081908190808, 0x2b08081919080808,
-    0x2b08081919190819, 0x2b08081919192b19, 0x2b08082b08080808, 0x2b08082b082b0808,
-    0x2b08082b2b080808, 0x2b08082b2b08082b, 0x2b08082b2b2b0808, 0x2b08082b2b2b2b08,
-    0x2b08190808080819, 0x2b08190808081908, 0x2b08190808190808, 0x2b0819080819082b,
-    0x2b08190808191919, 0x2b08190819080808, 0x2b081908192b0808, 0x2b0819082b082b19,
-    0x2b08191908080808, 0x2b08191919081908, 0x2b0819192b2b1919, 0x2b08192b08192b08,
-    0x2b08192b192b2b2b, 0x2b082b0808080808, 0x2b082b0808082b08, 0x2b082b08082b1919,
-    0x2b082b0819192b2b, 0x2b082b082b080808, 0x2b082b082b08082b, 0x2b082b082b2b2b08,
-    0x2b082b190808192b, 0x2b082b2b082b082b, 0x2b082b2b2b080808, 0x2b082b2b2b082b08,
-    0x2b082b2b2b19192b, 0x2b082b2b2b2b2b08, 0x2b19080808080819, 0x2b19080808081908,
-    0x2b19080808190808, 0x2b19080819080808, 0x2b1908081919192b, 0x2b1908082b081908,
-    0x2b19081908080808, 0x2b190819082b082b, 0x2b190819192b1908, 0x2b19082b1919192b,
-    0x2b19082b2b082b19, 0x2b19190808080808, 0x2b19190808081919, 0x2b19190819081908,
-    0x2b19190819190808, 0x2b19190819192b08, 0x2b191919082b2b19, 0x2b1919192b190808,
-    0x2b1919192b19082b, 0x2b19192b19080819, 0x2b192b0819190819, 0x2b192b082b2b192b,
-    0x2b192b1919082b19, 0x2b192b2b08191919, 0x2b192b2b192b0808, 0x2b2b080808080808,
-    0x2b2b08080808082b, 0x2b2b080808082b08, 0x2b2b080808082b2b, 0x2b2b0808082b0808,
-    0x2b2b0808082b2b2b, 0x2b2b08082b2b0808, 0x2b2b081919190819, 0x2b2b081919192b19,
-    0x2b2b08192b2b192b, 0x2b2b082b08080808, 0x2b2b082b0808082b, 0x2b2b082b08082b08,
-    0x2b2b082b082b2b2b, 0x2b2b082b2b080808, 0x2b2b082b2b2b0808, 0x2b2b190819080808,
-    0x2b2b19082b191919, 0x2b2b192b192b1919, 0x2b2b192b2b192b08, 0x2b2b2b0808082b2b,
-    0x2b2b2b08082b0808, 0x2b2b2b08082b082b, 0x2b2b2b08082b2b08, 0x2b2b2b082b2b0808,
-    0x2b2b2b082b2b2b08, 0x2b2b2b1908081908, 0x2b2b2b192b081908, 0x2b2b2b192b08192b,
-    0x2b2b2b2b082b2b08, 0x2b2b2b2b082b2b2b, 0x2b2b2b2b2b190819, 0x2b2b2b2b2b2b2b2b,
-};
-
-constexpr constant static uint64_t iq2s_grid[1024] = {
-    0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08,
-    0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x080808080819192b,
-    0x0808080808192b19, 0x08080808082b0808, 0x08080808082b082b, 0x08080808082b1919,
-    0x08080808082b2b08, 0x0808080819080819, 0x0808080819081908, 0x080808081908192b,
-    0x0808080819082b19, 0x0808080819190808, 0x080808081919082b, 0x0808080819191919,
-    0x0808080819192b08, 0x08080808192b0819, 0x08080808192b1908, 0x08080808192b192b,
-    0x08080808192b2b19, 0x080808082b080808, 0x080808082b08082b, 0x080808082b081919,
-    0x080808082b082b08, 0x080808082b190819, 0x080808082b191908, 0x080808082b2b0808,
-    0x080808082b2b1919, 0x080808082b2b2b2b, 0x0808081908080819, 0x0808081908081908,
-    0x080808190808192b, 0x0808081908082b19, 0x0808081908190808, 0x080808190819082b,
-    0x0808081908191919, 0x0808081908192b08, 0x08080819082b0819, 0x08080819082b1908,
-    0x0808081919080808, 0x080808191908082b, 0x0808081919081919, 0x0808081919082b08,
-    0x0808081919190819, 0x0808081919191908, 0x080808191919192b, 0x0808081919192b19,
-    0x08080819192b0808, 0x08080819192b1919, 0x08080819192b2b08, 0x080808192b080819,
-    0x080808192b081908, 0x080808192b190808, 0x080808192b19082b, 0x080808192b191919,
-    0x080808192b2b0819, 0x080808192b2b1908, 0x0808082b08080808, 0x0808082b0808082b,
-    0x0808082b08081919, 0x0808082b08082b08, 0x0808082b08190819, 0x0808082b08191908,
-    0x0808082b082b0808, 0x0808082b082b2b2b, 0x0808082b19080819, 0x0808082b19081908,
-    0x0808082b1908192b, 0x0808082b19082b19, 0x0808082b19190808, 0x0808082b19191919,
-    0x0808082b2b080808, 0x0808082b2b081919, 0x0808082b2b082b2b, 0x0808082b2b191908,
-    0x0808082b2b2b082b, 0x0808190808080819, 0x0808190808081908, 0x080819080808192b,
-    0x0808190808082b19, 0x0808190808190808, 0x080819080819082b, 0x0808190808191919,
-    0x0808190808192b08, 0x08081908082b0819, 0x08081908082b1908, 0x08081908082b192b,
-    0x08081908082b2b19, 0x0808190819080808, 0x080819081908082b, 0x0808190819081919,
-    0x0808190819082b08, 0x0808190819082b2b, 0x0808190819190819, 0x0808190819191908,
-    0x080819081919192b, 0x0808190819192b19, 0x08081908192b0808, 0x08081908192b082b,
-    0x08081908192b1919, 0x080819082b080819, 0x080819082b081908, 0x080819082b08192b,
-    0x080819082b082b19, 0x080819082b190808, 0x080819082b191919, 0x080819082b192b08,
-    0x080819082b2b0819, 0x080819082b2b1908, 0x0808191908080808, 0x080819190808082b,
-    0x0808191908081919, 0x0808191908082b08, 0x0808191908082b2b, 0x0808191908190819,
-    0x0808191908191908, 0x080819190819192b, 0x0808191908192b19, 0x08081919082b0808,
-    0x08081919082b1919, 0x08081919082b2b08, 0x0808191919080819, 0x0808191919081908,
-    0x080819191908192b, 0x0808191919082b19, 0x0808191919190808, 0x080819191919082b,
-    0x0808191919191919, 0x0808191919192b08, 0x08081919192b0819, 0x08081919192b1908,
-    0x080819192b080808, 0x080819192b08082b, 0x080819192b081919, 0x080819192b082b08,
-    0x080819192b190819, 0x080819192b191908, 0x080819192b2b0808, 0x0808192b08080819,
-    0x0808192b08081908, 0x0808192b0808192b, 0x0808192b08082b19, 0x0808192b08190808,
-    0x0808192b08191919, 0x0808192b19080808, 0x0808192b19081919, 0x0808192b19082b08,
-    0x0808192b19190819, 0x0808192b19191908, 0x0808192b192b0808, 0x0808192b2b080819,
-    0x0808192b2b081908, 0x0808192b2b190808, 0x08082b0808080808, 0x08082b080808082b,
-    0x08082b0808081919, 0x08082b0808082b08, 0x08082b0808190819, 0x08082b0808191908,
-    0x08082b080819192b, 0x08082b0808192b19, 0x08082b08082b0808, 0x08082b08082b1919,
-    0x08082b08082b2b2b, 0x08082b0819080819, 0x08082b0819081908, 0x08082b081908192b,
-    0x08082b0819082b19, 0x08082b0819190808, 0x08082b081919082b, 0x08082b0819191919,
-    0x08082b0819192b08, 0x08082b08192b0819, 0x08082b08192b1908, 0x08082b082b080808,
-    0x08082b082b081919, 0x08082b082b191908, 0x08082b082b2b2b2b, 0x08082b1908080819,
-    0x08082b1908081908, 0x08082b1908190808, 0x08082b190819082b, 0x08082b1908191919,
-    0x08082b1908192b08, 0x08082b19082b0819, 0x08082b1919080808, 0x08082b1919081919,
-    0x08082b1919082b08, 0x08082b1919190819, 0x08082b1919191908, 0x08082b19192b0808,
-    0x08082b192b080819, 0x08082b192b190808, 0x08082b2b08080808, 0x08082b2b08190819,
-    0x08082b2b08191908, 0x08082b2b082b082b, 0x08082b2b082b2b08, 0x08082b2b082b2b2b,
-    0x08082b2b19190808, 0x08082b2b2b192b19, 0x0819080808080819, 0x0819080808081908,
-    0x081908080808192b, 0x0819080808082b19, 0x0819080808190808, 0x081908080819082b,
-    0x0819080808191919, 0x0819080808192b08, 0x08190808082b0819, 0x08190808082b1908,
-    0x08190808082b192b, 0x0819080819080808, 0x081908081908082b, 0x0819080819081919,
-    0x0819080819082b08, 0x0819080819190819, 0x0819080819191908, 0x081908081919192b,
-    0x0819080819192b19, 0x08190808192b0808, 0x08190808192b082b, 0x08190808192b1919,
-    0x08190808192b2b08, 0x081908082b080819, 0x081908082b081908, 0x081908082b08192b,
-    0x081908082b190808, 0x081908082b191919, 0x081908082b192b08, 0x081908082b2b0819,
-    0x081908082b2b1908, 0x0819081908080808, 0x081908190808082b, 0x0819081908081919,
-    0x0819081908082b08, 0x0819081908082b2b, 0x0819081908190819, 0x0819081908191908,
-    0x081908190819192b, 0x0819081908192b19, 0x08190819082b0808, 0x08190819082b082b,
-    0x08190819082b1919, 0x08190819082b2b08, 0x0819081919080819, 0x0819081919081908,
-    0x081908191908192b, 0x0819081919082b19, 0x0819081919190808, 0x081908191919082b,
-    0x0819081919191919, 0x0819081919192b08, 0x08190819192b0819, 0x08190819192b1908,
-    0x081908192b080808, 0x081908192b08082b, 0x081908192b081919, 0x081908192b082b08,
-    0x081908192b190819, 0x081908192b191908, 0x0819082b08080819, 0x0819082b08081908,
-    0x0819082b08082b19, 0x0819082b08190808, 0x0819082b08191919, 0x0819082b082b0819,
-    0x0819082b082b1908, 0x0819082b19080808, 0x0819082b19081919, 0x0819082b19190819,
-    0x0819082b19191908, 0x0819082b2b080819, 0x0819082b2b081908, 0x0819082b2b190808,
-    0x0819190808080808, 0x081919080808082b, 0x0819190808081919, 0x0819190808082b08,
-    0x0819190808190819, 0x0819190808191908, 0x081919080819192b, 0x0819190808192b19,
-    0x08191908082b0808, 0x08191908082b1919, 0x08191908082b2b08, 0x0819190819080819,
-    0x0819190819081908, 0x081919081908192b, 0x0819190819082b19, 0x0819190819190808,
-    0x081919081919082b, 0x0819190819191919, 0x0819190819192b08, 0x08191908192b0819,
-    0x08191908192b1908, 0x081919082b080808, 0x081919082b08082b, 0x081919082b081919,
-    0x081919082b082b08, 0x081919082b190819, 0x081919082b191908, 0x081919082b2b0808,
-    0x0819191908080819, 0x0819191908081908, 0x081919190808192b, 0x0819191908082b19,
-    0x0819191908190808, 0x081919190819082b, 0x0819191908191919, 0x0819191908192b08,
-    0x08191919082b0819, 0x08191919082b1908, 0x0819191919080808, 0x081919191908082b,
-    0x0819191919081919, 0x0819191919082b08, 0x0819191919190819, 0x0819191919191908,
-    0x08191919192b0808, 0x081919192b080819, 0x081919192b081908, 0x081919192b190808,
-    0x0819192b08080808, 0x0819192b08081919, 0x0819192b08082b08, 0x0819192b08190819,
-    0x0819192b08191908, 0x0819192b082b0808, 0x0819192b19080819, 0x0819192b19081908,
-    0x0819192b19190808, 0x0819192b2b080808, 0x0819192b2b2b2b2b, 0x08192b0808080819,
-    0x08192b0808081908, 0x08192b080808192b, 0x08192b0808082b19, 0x08192b0808190808,
-    0x08192b0808191919, 0x08192b0808192b08, 0x08192b08082b0819, 0x08192b0819080808,
-    0x08192b081908082b, 0x08192b0819081919, 0x08192b0819082b08, 0x08192b0819190819,
-    0x08192b0819191908, 0x08192b08192b0808, 0x08192b082b080819, 0x08192b082b081908,
-    0x08192b1908080808, 0x08192b190808082b, 0x08192b1908081919, 0x08192b1908082b08,
-    0x08192b1908190819, 0x08192b1908191908, 0x08192b19082b0808, 0x08192b1919080819,
-    0x08192b1919081908, 0x08192b1919190808, 0x08192b19192b2b19, 0x08192b192b2b082b,
-    0x08192b2b08081908, 0x08192b2b08190808, 0x08192b2b19080808, 0x08192b2b1919192b,
-    0x082b080808080808, 0x082b08080808082b, 0x082b080808081919, 0x082b080808082b08,
-    0x082b080808190819, 0x082b080808191908, 0x082b08080819192b, 0x082b080808192b19,
-    0x082b0808082b0808, 0x082b0808082b1919, 0x082b0808082b2b2b, 0x082b080819080819,
-    0x082b080819081908, 0x082b080819190808, 0x082b08081919082b, 0x082b080819191919,
-    0x082b0808192b1908, 0x082b08082b080808, 0x082b08082b082b2b, 0x082b08082b191908,
-    0x082b08082b2b2b2b, 0x082b081908080819, 0x082b081908081908, 0x082b081908190808,
-    0x082b08190819082b, 0x082b081908191919, 0x082b0819082b0819, 0x082b081919080808,
-    0x082b08191908082b, 0x082b081919081919, 0x082b081919190819, 0x082b081919191908,
-    0x082b0819192b0808, 0x082b08192b080819, 0x082b08192b081908, 0x082b08192b190808,
-    0x082b082b08080808, 0x082b082b08082b2b, 0x082b082b082b082b, 0x082b082b082b2b08,
-    0x082b082b082b2b2b, 0x082b082b19081908, 0x082b082b19190808, 0x082b082b2b082b08,
-    0x082b082b2b082b2b, 0x082b082b2b2b2b08, 0x082b190808080819, 0x082b190808081908,
-    0x082b19080808192b, 0x082b190808082b19, 0x082b190808190808, 0x082b190808191919,
-    0x082b190808192b08, 0x082b1908082b0819, 0x082b1908082b1908, 0x082b190819080808,
-    0x082b19081908082b, 0x082b190819081919, 0x082b190819082b08, 0x082b190819190819,
-    0x082b190819191908, 0x082b1908192b0808, 0x082b19082b080819, 0x082b19082b081908,
-    0x082b19082b190808, 0x082b191908080808, 0x082b191908081919, 0x082b191908082b08,
-    0x082b191908190819, 0x082b191908191908, 0x082b1919082b0808, 0x082b191919080819,
-    0x082b191919081908, 0x082b191919190808, 0x082b1919192b192b, 0x082b19192b080808,
-    0x082b192b08080819, 0x082b192b08081908, 0x082b192b08190808, 0x082b192b19080808,
-    0x082b192b19192b19, 0x082b2b0808080808, 0x082b2b0808081919, 0x082b2b0808190819,
-    0x082b2b0808191908, 0x082b2b0819080819, 0x082b2b0819081908, 0x082b2b0819190808,
-    0x082b2b082b082b2b, 0x082b2b082b2b2b2b, 0x082b2b1908080819, 0x082b2b1908081908,
-    0x082b2b1908190808, 0x082b2b192b191919, 0x082b2b2b08082b2b, 0x082b2b2b082b082b,
-    0x082b2b2b192b1908, 0x082b2b2b2b082b08, 0x082b2b2b2b082b2b, 0x1908080808080819,
-    0x1908080808081908, 0x190808080808192b, 0x1908080808082b19, 0x1908080808190808,
-    0x190808080819082b, 0x1908080808191919, 0x1908080808192b08, 0x1908080808192b2b,
-    0x19080808082b0819, 0x19080808082b1908, 0x19080808082b192b, 0x1908080819080808,
-    0x190808081908082b, 0x1908080819081919, 0x1908080819082b08, 0x1908080819082b2b,
-    0x1908080819190819, 0x1908080819191908, 0x190808081919192b, 0x1908080819192b19,
-    0x19080808192b0808, 0x19080808192b082b, 0x19080808192b1919, 0x190808082b080819,
-    0x190808082b081908, 0x190808082b190808, 0x190808082b191919, 0x190808082b192b08,
-    0x190808082b2b0819, 0x190808082b2b1908, 0x1908081908080808, 0x190808190808082b,
-    0x1908081908081919, 0x1908081908082b08, 0x1908081908190819, 0x1908081908191908,
-    0x190808190819192b, 0x1908081908192b19, 0x19080819082b0808, 0x19080819082b082b,
-    0x19080819082b1919, 0x1908081919080819, 0x1908081919081908, 0x190808191908192b,
-    0x1908081919082b19, 0x1908081919190808, 0x190808191919082b, 0x1908081919191919,
-    0x1908081919192b08, 0x19080819192b0819, 0x19080819192b1908, 0x190808192b080808,
-    0x190808192b08082b, 0x190808192b081919, 0x190808192b082b08, 0x190808192b190819,
-    0x190808192b191908, 0x190808192b2b0808, 0x1908082b08080819, 0x1908082b08081908,
-    0x1908082b08190808, 0x1908082b0819082b, 0x1908082b08191919, 0x1908082b08192b08,
-    0x1908082b082b1908, 0x1908082b19080808, 0x1908082b19081919, 0x1908082b19082b08,
-    0x1908082b19190819, 0x1908082b19191908, 0x1908082b192b0808, 0x1908082b2b080819,
-    0x1908082b2b081908, 0x1908190808080808, 0x190819080808082b, 0x1908190808081919,
-    0x1908190808082b08, 0x1908190808082b2b, 0x1908190808190819, 0x1908190808191908,
-    0x190819080819192b, 0x1908190808192b19, 0x19081908082b0808, 0x19081908082b082b,
-    0x19081908082b1919, 0x19081908082b2b08, 0x1908190819080819, 0x1908190819081908,
-    0x190819081908192b, 0x1908190819082b19, 0x1908190819190808, 0x190819081919082b,
-    0x1908190819191919, 0x1908190819192b08, 0x19081908192b0819, 0x19081908192b1908,
-    0x190819082b080808, 0x190819082b08082b, 0x190819082b081919, 0x190819082b082b08,
-    0x190819082b190819, 0x190819082b191908, 0x190819082b2b0808, 0x1908191908080819,
-    0x1908191908081908, 0x190819190808192b, 0x1908191908082b19, 0x1908191908190808,
-    0x190819190819082b, 0x1908191908191919, 0x1908191908192b08, 0x19081919082b0819,
-    0x19081919082b1908, 0x1908191919080808, 0x190819191908082b, 0x1908191919081919,
-    0x1908191919082b08, 0x1908191919190819, 0x1908191919191908, 0x19081919192b0808,
-    0x19081919192b2b2b, 0x190819192b080819, 0x190819192b081908, 0x190819192b190808,
-    0x1908192b08080808, 0x1908192b0808082b, 0x1908192b08081919, 0x1908192b08082b08,
-    0x1908192b08190819, 0x1908192b08191908, 0x1908192b082b0808, 0x1908192b19080819,
-    0x1908192b19081908, 0x1908192b19190808, 0x1908192b2b080808, 0x1908192b2b2b1919,
-    0x19082b0808080819, 0x19082b0808081908, 0x19082b0808082b19, 0x19082b0808190808,
-    0x19082b080819082b, 0x19082b0808191919, 0x19082b0808192b08, 0x19082b08082b0819,
-    0x19082b08082b1908, 0x19082b0819080808, 0x19082b081908082b, 0x19082b0819081919,
-    0x19082b0819082b08, 0x19082b0819190819, 0x19082b0819191908, 0x19082b08192b0808,
-    0x19082b082b081908, 0x19082b082b190808, 0x19082b1908080808, 0x19082b190808082b,
-    0x19082b1908081919, 0x19082b1908082b08, 0x19082b1908190819, 0x19082b1908191908,
-    0x19082b19082b0808, 0x19082b1919080819, 0x19082b1919081908, 0x19082b1919190808,
-    0x19082b192b080808, 0x19082b192b19192b, 0x19082b2b08080819, 0x19082b2b08081908,
-    0x19082b2b08190808, 0x19082b2b19080808, 0x1919080808080808, 0x191908080808082b,
-    0x1919080808081919, 0x1919080808082b08, 0x1919080808190819, 0x1919080808191908,
-    0x191908080819192b, 0x1919080808192b19, 0x19190808082b0808, 0x19190808082b082b,
-    0x19190808082b1919, 0x19190808082b2b08, 0x1919080819080819, 0x1919080819081908,
-    0x191908081908192b, 0x1919080819082b19, 0x1919080819190808, 0x191908081919082b,
-    0x1919080819191919, 0x1919080819192b08, 0x19190808192b0819, 0x19190808192b1908,
-    0x191908082b080808, 0x191908082b08082b, 0x191908082b081919, 0x191908082b082b08,
-    0x191908082b190819, 0x191908082b191908, 0x1919081908080819, 0x1919081908081908,
-    0x191908190808192b, 0x1919081908082b19, 0x1919081908190808, 0x191908190819082b,
-    0x1919081908191919, 0x1919081908192b08, 0x19190819082b0819, 0x19190819082b1908,
-    0x1919081919080808, 0x191908191908082b, 0x1919081919081919, 0x1919081919082b08,
-    0x1919081919190819, 0x1919081919191908, 0x19190819192b0808, 0x191908192b080819,
-    0x191908192b081908, 0x191908192b190808, 0x1919082b08080808, 0x1919082b08081919,
-    0x1919082b08082b08, 0x1919082b08190819, 0x1919082b08191908, 0x1919082b082b0808,
-    0x1919082b19080819, 0x1919082b19081908, 0x1919082b19190808, 0x1919082b192b2b19,
-    0x1919082b2b080808, 0x1919190808080819, 0x1919190808081908, 0x191919080808192b,
-    0x1919190808082b19, 0x1919190808190808, 0x191919080819082b, 0x1919190808191919,
-    0x1919190808192b08, 0x19191908082b0819, 0x19191908082b1908, 0x1919190819080808,
-    0x191919081908082b, 0x1919190819081919, 0x1919190819082b08, 0x1919190819190819,
-    0x1919190819191908, 0x19191908192b0808, 0x191919082b080819, 0x191919082b081908,
-    0x191919082b190808, 0x1919191908080808, 0x191919190808082b, 0x1919191908081919,
-    0x1919191908082b08, 0x1919191908190819, 0x1919191908191908, 0x19191919082b0808,
-    0x1919191919080819, 0x1919191919081908, 0x1919191919190808, 0x191919192b080808,
-    0x1919192b08080819, 0x1919192b08081908, 0x1919192b08190808, 0x1919192b082b192b,
-    0x1919192b19080808, 0x19192b0808080808, 0x19192b080808082b, 0x19192b0808081919,
-    0x19192b0808082b08, 0x19192b0808190819, 0x19192b0808191908, 0x19192b08082b0808,
-    0x19192b0819080819, 0x19192b0819081908, 0x19192b0819190808, 0x19192b0819192b2b,
-    0x19192b082b080808, 0x19192b1908080819, 0x19192b1908081908, 0x19192b1908190808,
-    0x19192b1919080808, 0x19192b2b08080808, 0x19192b2b08192b19, 0x19192b2b2b081919,
-    0x19192b2b2b2b2b08, 0x192b080808080819, 0x192b080808081908, 0x192b08080808192b,
-    0x192b080808190808, 0x192b08080819082b, 0x192b080808191919, 0x192b080808192b08,
-    0x192b0808082b0819, 0x192b0808082b1908, 0x192b080819080808, 0x192b080819081919,
-    0x192b080819082b08, 0x192b080819190819, 0x192b080819191908, 0x192b0808192b0808,
-    0x192b08082b081908, 0x192b08082b190808, 0x192b081908080808, 0x192b08190808082b,
-    0x192b081908081919, 0x192b081908082b08, 0x192b081908190819, 0x192b081908191908,
-    0x192b0819082b0808, 0x192b081919080819, 0x192b081919081908, 0x192b081919190808,
-    0x192b08192b080808, 0x192b08192b192b19, 0x192b082b08081908, 0x192b082b08190808,
-    0x192b082b19080808, 0x192b082b1919192b, 0x192b082b2b2b0819, 0x192b190808080808,
-    0x192b190808081919, 0x192b190808082b08, 0x192b190808190819, 0x192b190808191908,
-    0x192b1908082b0808, 0x192b190819080819, 0x192b190819081908, 0x192b190819190808,
-    0x192b19082b080808, 0x192b191908080819, 0x192b191908081908, 0x192b191908190808,
-    0x192b191919080808, 0x192b191919082b2b, 0x192b1919192b2b08, 0x192b19192b19082b,
-    0x192b192b08080808, 0x192b192b2b191908, 0x192b2b0808080819, 0x192b2b0808081908,
-    0x192b2b0808190808, 0x192b2b08192b1919, 0x192b2b082b192b08, 0x192b2b1908080808,
-    0x192b2b19082b2b2b, 0x192b2b2b1908082b, 0x192b2b2b2b2b0819, 0x2b08080808080808,
-    0x2b0808080808082b, 0x2b08080808081919, 0x2b08080808082b08, 0x2b08080808190819,
-    0x2b08080808191908, 0x2b08080808192b19, 0x2b080808082b0808, 0x2b080808082b1919,
-    0x2b08080819080819, 0x2b08080819081908, 0x2b08080819190808, 0x2b0808081919082b,
-    0x2b08080819191919, 0x2b08080819192b08, 0x2b080808192b0819, 0x2b0808082b080808,
-    0x2b0808082b081919, 0x2b0808082b190819, 0x2b0808082b191908, 0x2b08081908080819,
-    0x2b08081908081908, 0x2b08081908082b19, 0x2b08081908190808, 0x2b0808190819082b,
-    0x2b08081908191919, 0x2b08081908192b08, 0x2b080819082b0819, 0x2b080819082b1908,
-    0x2b08081919080808, 0x2b0808191908082b, 0x2b08081919081919, 0x2b08081919082b08,
-    0x2b08081919190819, 0x2b08081919191908, 0x2b0808192b080819, 0x2b0808192b081908,
-    0x2b0808192b190808, 0x2b0808192b2b2b19, 0x2b08082b08080808, 0x2b08082b08081919,
-    0x2b08082b08082b2b, 0x2b08082b08190819, 0x2b08082b08191908, 0x2b08082b19080819,
-    0x2b08082b19081908, 0x2b08082b19190808, 0x2b08190808080819, 0x2b08190808081908,
-    0x2b0819080808192b, 0x2b08190808082b19, 0x2b08190808190808, 0x2b0819080819082b,
-    0x2b08190808191919, 0x2b08190808192b08, 0x2b081908082b0819, 0x2b08190819080808,
-    0x2b0819081908082b, 0x2b08190819081919, 0x2b08190819082b08, 0x2b08190819190819,
-    0x2b08190819191908, 0x2b081908192b0808, 0x2b0819082b080819, 0x2b0819082b081908,
-    0x2b0819082b190808, 0x2b08191908080808, 0x2b0819190808082b, 0x2b08191908081919,
-    0x2b08191908082b08, 0x2b08191908190819, 0x2b08191908191908, 0x2b081919082b0808,
-    0x2b08191919080819, 0x2b08191919081908, 0x2b08191919190808, 0x2b0819192b080808,
-    0x2b0819192b082b2b, 0x2b08192b08080819, 0x2b08192b08081908, 0x2b08192b08190808,
-    0x2b08192b082b2b19, 0x2b08192b19080808, 0x2b082b0808080808, 0x2b082b0808081919,
-    0x2b082b0808190819, 0x2b082b0808191908, 0x2b082b0819080819, 0x2b082b0819081908,
-    0x2b082b0819190808, 0x2b082b082b2b082b, 0x2b082b1908080819, 0x2b082b1908081908,
-    0x2b082b1919080808, 0x2b082b19192b1919, 0x2b082b2b082b082b, 0x2b082b2b19192b08,
-    0x2b082b2b19192b2b, 0x2b082b2b2b08082b, 0x2b082b2b2b2b082b, 0x2b19080808080819,
-    0x2b19080808081908, 0x2b19080808082b19, 0x2b19080808190808, 0x2b1908080819082b,
-    0x2b19080808191919, 0x2b19080808192b08, 0x2b190808082b1908, 0x2b19080819080808,
-    0x2b1908081908082b, 0x2b19080819081919, 0x2b19080819082b08, 0x2b19080819190819,
-    0x2b19080819191908, 0x2b190808192b0808, 0x2b1908082b080819, 0x2b1908082b081908,
-    0x2b1908082b190808, 0x2b19081908080808, 0x2b19081908081919, 0x2b19081908190819,
-    0x2b19081908191908, 0x2b19081919080819, 0x2b19081919081908, 0x2b19081919190808,
-    0x2b19081919192b2b, 0x2b19082b08080819, 0x2b19082b08081908, 0x2b19082b08190808,
-    0x2b19082b19080808, 0x2b19082b2b2b192b, 0x2b19190808080808, 0x2b1919080808082b,
-    0x2b19190808081919, 0x2b19190808082b08, 0x2b19190808190819, 0x2b19190808191908,
-    0x2b191908082b0808, 0x2b19190819080819, 0x2b19190819081908, 0x2b19190819190808,
-    0x2b1919082b080808, 0x2b1919082b19192b, 0x2b19191908080819, 0x2b19191908081908,
-    0x2b19191908190808, 0x2b19191919080808, 0x2b1919192b192b08, 0x2b1919192b2b0819,
-    0x2b19192b08080808, 0x2b19192b1908192b, 0x2b19192b192b1908, 0x2b192b0808080819,
-    0x2b192b0808081908, 0x2b192b0808190808, 0x2b192b08082b192b, 0x2b192b0819080808,
-    0x2b192b082b2b2b19, 0x2b192b1908080808, 0x2b192b1919082b19, 0x2b192b191919082b,
-    0x2b192b2b2b190808, 0x2b2b080808080808, 0x2b2b080808081919, 0x2b2b080808082b2b,
-    0x2b2b080808191908, 0x2b2b0808082b082b, 0x2b2b0808082b2b2b, 0x2b2b080819080819,
-    0x2b2b080819081908, 0x2b2b080819190808, 0x2b2b08082b2b082b, 0x2b2b08082b2b2b2b,
-    0x2b2b081919080808, 0x2b2b0819192b1919, 0x2b2b082b0808082b, 0x2b2b082b08082b2b,
-    0x2b2b082b082b082b, 0x2b2b082b082b2b08, 0x2b2b082b082b2b2b, 0x2b2b082b2b08082b,
-    0x2b2b082b2b082b08, 0x2b2b082b2b082b2b, 0x2b2b082b2b2b2b08, 0x2b2b190808080819,
-    0x2b2b190808081908, 0x2b2b190808190808, 0x2b2b190819080808, 0x2b2b19082b082b19,
-    0x2b2b19082b2b1908, 0x2b2b191908080808, 0x2b2b191908192b19, 0x2b2b192b19190819,
-    0x2b2b2b0808082b2b, 0x2b2b2b08082b2b08, 0x2b2b2b082b2b082b, 0x2b2b2b1919191908,
-    0x2b2b2b192b08192b, 0x2b2b2b2b08082b08, 0x2b2b2b2b08082b2b, 0x2b2b2b2b082b0808,
-    0x2b2b2b2b082b082b, 0x2b2b2b2b082b2b08, 0x2b2b2b2b2b082b08, 0x2b2b2b2b2b2b2b2b,
-};
-
-constexpr constant static uint32_t iq3xxs_grid[256] = {
-    0x04040404, 0x04040414, 0x04040424, 0x04040c0c, 0x04040c1c, 0x04040c3e, 0x04041404, 0x04041414,
-    0x04041c0c, 0x04042414, 0x04043e1c, 0x04043e2c, 0x040c040c, 0x040c041c, 0x040c0c04, 0x040c0c14,
-    0x040c140c, 0x040c142c, 0x040c1c04, 0x040c1c14, 0x040c240c, 0x040c2c24, 0x040c3e04, 0x04140404,
-    0x04140414, 0x04140424, 0x04140c0c, 0x04141404, 0x04141414, 0x04141c0c, 0x04141c1c, 0x04141c3e,
-    0x04142c0c, 0x04142c3e, 0x04143e2c, 0x041c040c, 0x041c043e, 0x041c0c04, 0x041c0c14, 0x041c142c,
-    0x041c3e04, 0x04240c1c, 0x04241c3e, 0x04242424, 0x04242c3e, 0x04243e1c, 0x04243e2c, 0x042c040c,
-    0x042c043e, 0x042c1c14, 0x042c2c14, 0x04341c2c, 0x04343424, 0x043e0c04, 0x043e0c24, 0x043e0c34,
-    0x043e241c, 0x043e340c, 0x0c04040c, 0x0c04041c, 0x0c040c04, 0x0c040c14, 0x0c04140c, 0x0c04141c,
-    0x0c041c04, 0x0c041c14, 0x0c041c24, 0x0c04243e, 0x0c042c04, 0x0c0c0404, 0x0c0c0414, 0x0c0c0c0c,
-    0x0c0c1404, 0x0c0c1414, 0x0c14040c, 0x0c14041c, 0x0c140c04, 0x0c140c14, 0x0c14140c, 0x0c141c04,
-    0x0c143e14, 0x0c1c0404, 0x0c1c0414, 0x0c1c1404, 0x0c1c1c0c, 0x0c1c2434, 0x0c1c3434, 0x0c24040c,
-    0x0c24042c, 0x0c242c04, 0x0c2c1404, 0x0c2c1424, 0x0c2c2434, 0x0c2c3e0c, 0x0c34042c, 0x0c3e1414,
-    0x0c3e2404, 0x14040404, 0x14040414, 0x14040c0c, 0x14040c1c, 0x14041404, 0x14041414, 0x14041434,
-    0x14041c0c, 0x14042414, 0x140c040c, 0x140c041c, 0x140c042c, 0x140c0c04, 0x140c0c14, 0x140c140c,
-    0x140c1c04, 0x140c341c, 0x140c343e, 0x140c3e04, 0x14140404, 0x14140414, 0x14140c0c, 0x14140c3e,
-    0x14141404, 0x14141414, 0x14141c3e, 0x14142404, 0x14142c2c, 0x141c040c, 0x141c0c04, 0x141c0c24,
-    0x141c3e04, 0x141c3e24, 0x14241c2c, 0x14242c1c, 0x142c041c, 0x142c143e, 0x142c240c, 0x142c3e24,
-    0x143e040c, 0x143e041c, 0x143e0c34, 0x143e242c, 0x1c04040c, 0x1c040c04, 0x1c040c14, 0x1c04140c,
-    0x1c04141c, 0x1c042c04, 0x1c04342c, 0x1c043e14, 0x1c0c0404, 0x1c0c0414, 0x1c0c1404, 0x1c0c1c0c,
-    0x1c0c2424, 0x1c0c2434, 0x1c14040c, 0x1c14041c, 0x1c140c04, 0x1c14142c, 0x1c142c14, 0x1c143e14,
-    0x1c1c0c0c, 0x1c1c1c1c, 0x1c241c04, 0x1c24243e, 0x1c243e14, 0x1c2c0404, 0x1c2c0434, 0x1c2c1414,
-    0x1c2c2c2c, 0x1c340c24, 0x1c341c34, 0x1c34341c, 0x1c3e1c1c, 0x1c3e3404, 0x24040424, 0x24040c3e,
-    0x24041c2c, 0x24041c3e, 0x24042c1c, 0x24042c3e, 0x240c3e24, 0x24141404, 0x24141c3e, 0x24142404,
-    0x24143404, 0x24143434, 0x241c043e, 0x241c242c, 0x24240424, 0x24242c0c, 0x24243424, 0x242c142c,
-    0x242c241c, 0x242c3e04, 0x243e042c, 0x243e0c04, 0x243e0c14, 0x243e1c04, 0x2c040c14, 0x2c04240c,
-    0x2c043e04, 0x2c0c0404, 0x2c0c0434, 0x2c0c1434, 0x2c0c2c2c, 0x2c140c24, 0x2c141c14, 0x2c143e14,
-    0x2c1c0414, 0x2c1c2c1c, 0x2c240c04, 0x2c24141c, 0x2c24143e, 0x2c243e14, 0x2c2c0414, 0x2c2c1c0c,
-    0x2c342c04, 0x2c3e1424, 0x2c3e2414, 0x34041424, 0x34042424, 0x34042434, 0x34043424, 0x340c140c,
-    0x340c340c, 0x34140c3e, 0x34143424, 0x341c1c04, 0x341c1c34, 0x34242424, 0x342c042c, 0x342c2c14,
-    0x34341c1c, 0x343e041c, 0x343e140c, 0x3e04041c, 0x3e04042c, 0x3e04043e, 0x3e040c04, 0x3e041c14,
-    0x3e042c14, 0x3e0c1434, 0x3e0c2404, 0x3e140c14, 0x3e14242c, 0x3e142c14, 0x3e1c0404, 0x3e1c0c2c,
-    0x3e1c1c1c, 0x3e1c3404, 0x3e24140c, 0x3e24240c, 0x3e2c0404, 0x3e2c0414, 0x3e2c1424, 0x3e341c04,
-};
-
-constexpr constant static uint32_t iq3s_grid[512] = {
-    0x01010101, 0x01010103, 0x01010105, 0x0101010b, 0x0101010f, 0x01010301, 0x01010303, 0x01010305,
-    0x01010309, 0x0101030d, 0x01010501, 0x01010503, 0x0101050b, 0x01010707, 0x01010901, 0x01010905,
-    0x0101090b, 0x0101090f, 0x01010b03, 0x01010b07, 0x01010d01, 0x01010d05, 0x01010f03, 0x01010f09,
-    0x01010f0f, 0x01030101, 0x01030103, 0x01030105, 0x01030109, 0x01030301, 0x01030303, 0x0103030b,
-    0x01030501, 0x01030507, 0x0103050f, 0x01030703, 0x0103070b, 0x01030909, 0x01030d03, 0x01030d0b,
-    0x01030f05, 0x01050101, 0x01050103, 0x0105010b, 0x0105010f, 0x01050301, 0x01050307, 0x0105030d,
-    0x01050503, 0x0105050b, 0x01050701, 0x01050709, 0x01050905, 0x0105090b, 0x0105090f, 0x01050b03,
-    0x01050b07, 0x01050f01, 0x01050f07, 0x01070107, 0x01070303, 0x0107030b, 0x01070501, 0x01070505,
-    0x01070703, 0x01070707, 0x0107070d, 0x01070909, 0x01070b01, 0x01070b05, 0x01070d0f, 0x01070f03,
-    0x01070f0b, 0x01090101, 0x01090307, 0x0109030f, 0x01090503, 0x01090509, 0x01090705, 0x01090901,
-    0x01090907, 0x01090b03, 0x01090f01, 0x010b0105, 0x010b0109, 0x010b0501, 0x010b0505, 0x010b050d,
-    0x010b0707, 0x010b0903, 0x010b090b, 0x010b090f, 0x010b0d0d, 0x010b0f07, 0x010d010d, 0x010d0303,
-    0x010d0307, 0x010d0703, 0x010d0b05, 0x010d0f03, 0x010f0101, 0x010f0105, 0x010f0109, 0x010f0501,
-    0x010f0505, 0x010f050d, 0x010f0707, 0x010f0b01, 0x010f0b09, 0x03010101, 0x03010103, 0x03010105,
-    0x03010109, 0x03010301, 0x03010303, 0x03010307, 0x0301030b, 0x0301030f, 0x03010501, 0x03010505,
-    0x03010703, 0x03010709, 0x0301070d, 0x03010b09, 0x03010b0d, 0x03010d03, 0x03010f05, 0x03030101,
-    0x03030103, 0x03030107, 0x0303010d, 0x03030301, 0x03030309, 0x03030503, 0x03030701, 0x03030707,
-    0x03030903, 0x03030b01, 0x03030b05, 0x03030f01, 0x03030f0d, 0x03050101, 0x03050305, 0x0305030b,
-    0x0305030f, 0x03050501, 0x03050509, 0x03050705, 0x03050901, 0x03050907, 0x03050b0b, 0x03050d01,
-    0x03050f05, 0x03070103, 0x03070109, 0x0307010f, 0x03070301, 0x03070307, 0x03070503, 0x0307050f,
-    0x03070701, 0x03070709, 0x03070903, 0x03070d05, 0x03070f01, 0x03090107, 0x0309010b, 0x03090305,
-    0x03090309, 0x03090703, 0x03090707, 0x03090905, 0x0309090d, 0x03090b01, 0x03090b09, 0x030b0103,
-    0x030b0301, 0x030b0307, 0x030b0503, 0x030b0701, 0x030b0705, 0x030b0b03, 0x030d0501, 0x030d0509,
-    0x030d050f, 0x030d0909, 0x030d090d, 0x030f0103, 0x030f0107, 0x030f0301, 0x030f0305, 0x030f0503,
-    0x030f070b, 0x030f0903, 0x030f0d05, 0x030f0f01, 0x05010101, 0x05010103, 0x05010107, 0x0501010b,
-    0x0501010f, 0x05010301, 0x05010305, 0x05010309, 0x0501030d, 0x05010503, 0x05010507, 0x0501050f,
-    0x05010701, 0x05010705, 0x05010903, 0x05010907, 0x0501090b, 0x05010b01, 0x05010b05, 0x05010d0f,
-    0x05010f01, 0x05010f07, 0x05010f0b, 0x05030101, 0x05030105, 0x05030301, 0x05030307, 0x0503030f,
-    0x05030505, 0x0503050b, 0x05030703, 0x05030709, 0x05030905, 0x05030b03, 0x05050103, 0x05050109,
-    0x0505010f, 0x05050503, 0x05050507, 0x05050701, 0x0505070f, 0x05050903, 0x05050b07, 0x05050b0f,
-    0x05050f03, 0x05050f09, 0x05070101, 0x05070105, 0x0507010b, 0x05070303, 0x05070505, 0x05070509,
-    0x05070703, 0x05070707, 0x05070905, 0x05070b01, 0x05070d0d, 0x05090103, 0x0509010f, 0x05090501,
-    0x05090507, 0x05090705, 0x0509070b, 0x05090903, 0x05090f05, 0x05090f0b, 0x050b0109, 0x050b0303,
-    0x050b0505, 0x050b070f, 0x050b0901, 0x050b0b07, 0x050b0f01, 0x050d0101, 0x050d0105, 0x050d010f,
-    0x050d0503, 0x050d0b0b, 0x050d0d03, 0x050f010b, 0x050f0303, 0x050f050d, 0x050f0701, 0x050f0907,
-    0x050f0b01, 0x07010105, 0x07010303, 0x07010307, 0x0701030b, 0x0701030f, 0x07010505, 0x07010703,
-    0x07010707, 0x0701070b, 0x07010905, 0x07010909, 0x0701090f, 0x07010b03, 0x07010d07, 0x07010f03,
-    0x07030103, 0x07030107, 0x0703010b, 0x07030309, 0x07030503, 0x07030507, 0x07030901, 0x07030d01,
-    0x07030f05, 0x07030f0d, 0x07050101, 0x07050305, 0x07050501, 0x07050705, 0x07050709, 0x07050b01,
-    0x07070103, 0x07070301, 0x07070309, 0x07070503, 0x07070507, 0x0707050f, 0x07070701, 0x07070903,
-    0x07070907, 0x0707090f, 0x07070b0b, 0x07070f07, 0x07090107, 0x07090303, 0x0709030d, 0x07090505,
-    0x07090703, 0x07090b05, 0x07090d01, 0x07090d09, 0x070b0103, 0x070b0301, 0x070b0305, 0x070b050b,
-    0x070b0705, 0x070b0909, 0x070b0b0d, 0x070b0f07, 0x070d030d, 0x070d0903, 0x070f0103, 0x070f0107,
-    0x070f0501, 0x070f0505, 0x070f070b, 0x09010101, 0x09010109, 0x09010305, 0x09010501, 0x09010509,
-    0x0901050f, 0x09010705, 0x09010903, 0x09010b01, 0x09010f01, 0x09030105, 0x0903010f, 0x09030303,
-    0x09030307, 0x09030505, 0x09030701, 0x0903070b, 0x09030907, 0x09030b03, 0x09030b0b, 0x09050103,
-    0x09050107, 0x09050301, 0x0905030b, 0x09050503, 0x09050707, 0x09050901, 0x09050b0f, 0x09050d05,
-    0x09050f01, 0x09070109, 0x09070303, 0x09070307, 0x09070501, 0x09070505, 0x09070703, 0x0907070b,
-    0x09090101, 0x09090105, 0x09090509, 0x0909070f, 0x09090901, 0x09090f03, 0x090b010b, 0x090b010f,
-    0x090b0503, 0x090b0d05, 0x090d0307, 0x090d0709, 0x090d0d01, 0x090f0301, 0x090f030b, 0x090f0701,
-    0x090f0907, 0x090f0b03, 0x0b010105, 0x0b010301, 0x0b010309, 0x0b010505, 0x0b010901, 0x0b010909,
-    0x0b01090f, 0x0b010b05, 0x0b010d0d, 0x0b010f09, 0x0b030103, 0x0b030107, 0x0b03010b, 0x0b030305,
-    0x0b030503, 0x0b030705, 0x0b030f05, 0x0b050101, 0x0b050303, 0x0b050507, 0x0b050701, 0x0b05070d,
-    0x0b050b07, 0x0b070105, 0x0b07010f, 0x0b070301, 0x0b07050f, 0x0b070909, 0x0b070b03, 0x0b070d0b,
-    0x0b070f07, 0x0b090103, 0x0b090109, 0x0b090501, 0x0b090705, 0x0b09090d, 0x0b0b0305, 0x0b0b050d,
-    0x0b0b0b03, 0x0b0b0b07, 0x0b0d0905, 0x0b0f0105, 0x0b0f0109, 0x0b0f0505, 0x0d010303, 0x0d010307,
-    0x0d01030b, 0x0d010703, 0x0d010707, 0x0d010d01, 0x0d030101, 0x0d030501, 0x0d03050f, 0x0d030d09,
-    0x0d050305, 0x0d050709, 0x0d050905, 0x0d050b0b, 0x0d050d05, 0x0d050f01, 0x0d070101, 0x0d070309,
-    0x0d070503, 0x0d070901, 0x0d09050b, 0x0d090907, 0x0d090d05, 0x0d0b0101, 0x0d0b0107, 0x0d0b0709,
-    0x0d0b0d01, 0x0d0d010b, 0x0d0d0901, 0x0d0f0303, 0x0d0f0307, 0x0f010101, 0x0f010109, 0x0f01010f,
-    0x0f010501, 0x0f010505, 0x0f01070d, 0x0f010901, 0x0f010b09, 0x0f010d05, 0x0f030105, 0x0f030303,
-    0x0f030509, 0x0f030907, 0x0f03090b, 0x0f050103, 0x0f050109, 0x0f050301, 0x0f05030d, 0x0f050503,
-    0x0f050701, 0x0f050b03, 0x0f070105, 0x0f070705, 0x0f07070b, 0x0f070b07, 0x0f090103, 0x0f09010b,
-    0x0f090307, 0x0f090501, 0x0f090b01, 0x0f0b0505, 0x0f0b0905, 0x0f0d0105, 0x0f0d0703, 0x0f0f0101,
-};
-
-#define NGRID_IQ1S 512
-constexpr constant static uint64_t iq1s_grid[NGRID_IQ1S] = {
-    0xffffffffffff0101, 0xffffffffff01ff00, 0xffffffffff010100, 0xffffffff00000000,
-    0xffffffff01ff00ff, 0xffffffff01ff0001, 0xffffffff0101ffff, 0xffffffff0101ff01,
-    0xffffff00ff000000, 0xffffff000000ff00, 0xffffff00000000ff, 0xffffff0000000100,
-    0xffffff0000010000, 0xffffff0001000000, 0xffffff01ffff00ff, 0xffffff01ff01ff00,
-    0xffffff01ff010100, 0xffffff0100000001, 0xffffff0101ffff00, 0xffffff0101ff0101,
-    0xffffff0101010100, 0xffff00ffff00ff01, 0xffff00ffff0000ff, 0xffff00ff00ff0100,
-    0xffff00ff0100ff00, 0xffff00ff010001ff, 0xffff0000ff0101ff, 0xffff000000ffff00,
-    0xffff000000000000, 0xffff00000001ff01, 0xffff000001000101, 0xffff0000010100ff,
-    0xffff0001ffff0100, 0xffff00010000ff00, 0xffff000100010101, 0xffff000101000000,
-    0xffff01ffffff0000, 0xffff01ffff01ffff, 0xffff01ffff010100, 0xffff01ff00000000,
-    0xffff01ff01ffffff, 0xffff01ff01ff0001, 0xffff01ff0101ffff, 0xffff01ff01010001,
-    0xffff0100ffffff01, 0xffff01000000ffff, 0xffff010000000100, 0xffff010001ff01ff,
-    0xffff010001000000, 0xffff0101ff000000, 0xffff0101000101ff, 0xffff010101ffff01,
-    0xffff01010101ff00, 0xff00ffffff000000, 0xff00ffff00ffff00, 0xff00ffff00000001,
-    0xff00ffff000001ff, 0xff00ffff01010000, 0xff00ff00ffff0000, 0xff00ff00ff00ff00,
-    0xff00ff00ff0000ff, 0xff00ff00ff000100, 0xff00ff00ff010001, 0xff00ff0000ff0001,
-    0xff00ff000000ffff, 0xff00ff0000000000, 0xff00ff000001ff00, 0xff00ff0000010100,
-    0xff00ff0001ff0000, 0xff00ff000100ff00, 0xff00ff0001000100, 0xff00ff01ff000000,
-    0xff00ff0100ff0000, 0xff00ff01000001ff, 0xff00ff0101010001, 0xff0000ff00000000,
-    0xff0000ff0001ff00, 0xff0000ff00010100, 0xff000000ffff0101, 0xff000000ff000000,
-    0xff000000ff01ff00, 0xff00000000ff0000, 0xff0000000000ff00, 0xff000000000000ff,
-    0xff00000000000000, 0xff00000000000001, 0xff00000000000100, 0xff0000000001ffff,
-    0xff00000000010000, 0xff00000001000000, 0xff00000001010100, 0xff000001ff00ff01,
-    0xff000001ff0100ff, 0xff00000100000000, 0xff0000010001ff00, 0xff00000101ff0100,
-    0xff0000010100ff00, 0xff0001ff00ff00ff, 0xff0001ff00000101, 0xff0001ff000100ff,
-    0xff0001ff01000000, 0xff000100ff0001ff, 0xff0001000000ff01, 0xff00010000000000,
-    0xff00010000010001, 0xff00010000010100, 0xff00010001ffff00, 0xff00010001ff0101,
-    0xff00010001010000, 0xff000101ffffffff, 0xff000101ff000101, 0xff00010101ff00ff,
-    0xff00010101000001, 0xff000101010100ff, 0xff01ffffff000101, 0xff01ffffff01ffff,
-    0xff01ffffff01ff01, 0xff01ffffff0101ff, 0xff01ffff00000000, 0xff01ffff01ff0001,
-    0xff01ffff0101ff01, 0xff01ff00ff000000, 0xff01ff0000ff0100, 0xff01ff000000ff01,
-    0xff01ff0000010000, 0xff01ff00010000ff, 0xff01ff01ff01ff00, 0xff01ff0100000101,
-    0xff0100ffffff0000, 0xff0100ffff010000, 0xff0100ff01ff00ff, 0xff0100ff01000100,
-    0xff0100ff010100ff, 0xff010000ffffff01, 0xff01000000000000, 0xff0100000101ff00,
-    0xff010001ffff00ff, 0xff010001ff000100, 0xff01000100ffff00, 0xff01000100010001,
-    0xff01000101ff0001, 0xff010001010001ff, 0xff0101ffffffffff, 0xff0101ffff01ffff,
-    0xff0101ffff010101, 0xff0101ff0000ff00, 0xff0101ff01010001, 0xff010100ff000000,
-    0xff010100ff01ff01, 0xff01010000ff0001, 0xff01010000000100, 0xff01010001000000,
-    0xff0101010100ffff, 0x00ffffff0000ff01, 0x00ffffff000000ff, 0x00ffffff00000100,
-    0x00ffffff00010000, 0x00ffff00ffff0001, 0x00ffff00ff0000ff, 0x00ffff00ff000100,
-    0x00ffff0000000000, 0x00ffff0001000100, 0x00ffff0001010001, 0x00ffff01ff00ff01,
-    0x00ffff0100ff0100, 0x00ffff010000ff00, 0x00ffff01000100ff, 0x00ffff0101ff00ff,
-    0x00ffff010101ff00, 0x00ff00ffffffffff, 0x00ff00ffffff01ff, 0x00ff00ffff000101,
-    0x00ff00ff00000000, 0x00ff00ff000101ff, 0x00ff00ff01010101, 0x00ff0000ff000000,
-    0x00ff0000ff01ffff, 0x00ff000000ff0000, 0x00ff00000000ff00, 0x00ff0000000000ff,
-    0x00ff000000000000, 0x00ff000000000001, 0x00ff000000000100, 0x00ff000000010000,
-    0x00ff000001ffff01, 0x00ff000001000000, 0x00ff0001ff000101, 0x00ff000100ffffff,
-    0x00ff000100000000, 0x00ff0001010001ff, 0x00ff01ffff000000, 0x00ff01ff0001ff00,
-    0x00ff01ff01ff0100, 0x00ff0100ff01ff01, 0x00ff010000ff00ff, 0x00ff010000ff0101,
-    0x00ff010000000000, 0x00ff010000010101, 0x00ff01000100ff00, 0x00ff010001010000,
-    0x00ff0101ffffff00, 0x00ff01010000ff01, 0x00ff010100000100, 0x00ff010101ff0000,
-    0x0000ffffffff0100, 0x0000ffffff00ff00, 0x0000ffffff0000ff, 0x0000ffffff010000,
-    0x0000ffff00000000, 0x0000ffff00010101, 0x0000ffff01ffff01, 0x0000ffff01000100,
-    0x0000ff00ff000000, 0x0000ff00ff01ff00, 0x0000ff00ff0101ff, 0x0000ff0000ff0000,
-    0x0000ff000000ff00, 0x0000ff00000000ff, 0x0000ff0000000000, 0x0000ff0000000001,
-    0x0000ff0000000100, 0x0000ff0000010000, 0x0000ff0001ffffff, 0x0000ff0001ff01ff,
-    0x0000ff0001000000, 0x0000ff000101ffff, 0x0000ff01ffff0101, 0x0000ff01ff010000,
-    0x0000ff0100000000, 0x0000ff0101000101, 0x000000ffffff0001, 0x000000ffff000000,
-    0x000000ff00ff0000, 0x000000ff0000ff00, 0x000000ff000000ff, 0x000000ff00000000,
-    0x000000ff00000001, 0x000000ff00000100, 0x000000ff00010000, 0x000000ff01000000,
-    0x000000ff0101ff00, 0x00000000ffff0000, 0x00000000ff00ff00, 0x00000000ff0000ff,
-    0x00000000ff000000, 0x00000000ff000001, 0x00000000ff000100, 0x00000000ff010000,
-    0x0000000000ffff00, 0x0000000000ff00ff, 0x0000000000ff0000, 0x0000000000ff0001,
-    0x0000000000ff0100, 0x000000000000ffff, 0x000000000000ff00, 0x000000000000ff01,
-    0x00000000000000ff, 0x0000000000000001, 0x00000000000001ff, 0x0000000000000100,
-    0x0000000000000101, 0x000000000001ff00, 0x00000000000100ff, 0x0000000000010000,
-    0x0000000000010001, 0x0000000000010100, 0x0000000001ff0000, 0x000000000100ff00,
-    0x00000000010000ff, 0x0000000001000000, 0x0000000001000001, 0x0000000001000100,
-    0x0000000001010000, 0x00000001ffff01ff, 0x00000001ff000000, 0x0000000100ff0000,
-    0x000000010000ff00, 0x00000001000000ff, 0x0000000100000000, 0x0000000100000001,
-    0x0000000100000100, 0x0000000100010000, 0x0000000101000000, 0x000001ffff00ff00,
-    0x000001ffff010001, 0x000001ffff0101ff, 0x000001ff00ffff01, 0x000001ff0000ffff,
-    0x000001ff00000000, 0x000001ff010000ff, 0x000001ff01010100, 0x00000100ffff0100,
-    0x00000100ff000000, 0x0000010000ff0000, 0x000001000000ff00, 0x00000100000000ff,
-    0x0000010000000000, 0x0000010000000001, 0x0000010000000100, 0x0000010000010000,
-    0x0000010001000000, 0x000001000101ff01, 0x00000101ffff0001, 0x00000101ff01ffff,
-    0x0000010100000000, 0x0000010101010100, 0x0001ffffff000000, 0x0001ffff00ffffff,
-    0x0001ffff00000100, 0x0001ffff0001ff00, 0x0001ffff01000000, 0x0001ff00ffffff00,
-    0x0001ff00ffff01ff, 0x0001ff00ff010000, 0x0001ff0000000000, 0x0001ff0000010001,
-    0x0001ff0001ff0000, 0x0001ff0001010100, 0x0001ff01ff0000ff, 0x0001ff01ff000001,
-    0x0001ff0100ffffff, 0x0001ff010001ffff, 0x0001ff01000101ff, 0x0001ff010100ff01,
-    0x000100ffff00ffff, 0x000100ffff00ff01, 0x000100ffff000100, 0x000100ff00000000,
-    0x000100ff000101ff, 0x000100ff01ff0101, 0x000100ff0100ffff, 0x000100ff01010101,
-    0x00010000ff000000, 0x00010000ff010100, 0x0001000000ff0000, 0x000100000000ff00,
-    0x00010000000000ff, 0x0001000000000000, 0x0001000000000001, 0x0001000000000100,
-    0x0001000000010000, 0x0001000001ffff01, 0x0001000001000000, 0x0001000100ff0101,
-    0x0001000100000000, 0x00010001010100ff, 0x000101ffffff01ff, 0x000101ffffff0101,
-    0x000101ff00010000, 0x000101ff01ff0000, 0x000101ff0100ff01, 0x00010100ffff0000,
-    0x0001010000000000, 0x000101000001ffff, 0x0001010000010101, 0x00010100010001ff,
-    0x00010101ff00ff00, 0x00010101ff010001, 0x0001010100ffffff, 0x0001010100ff01ff,
-    0x00010101000101ff, 0x0001010101ff0000, 0x000101010100ff01, 0x0001010101000101,
-    0x01ffffffffff0101, 0x01ffffffff01ffff, 0x01ffffffff01ff01, 0x01ffffffff0101ff,
-    0x01ffffffff010101, 0x01ffffff00000000, 0x01ffffff01ff01ff, 0x01ffffff01000101,
-    0x01ffffff0101ff01, 0x01ffffff010100ff, 0x01ffff000000ff00, 0x01ffff0000000001,
-    0x01ffff00000001ff, 0x01ffff0000010000, 0x01ffff0001ff0000, 0x01ffff01ffffffff,
-    0x01ffff01ffff01ff, 0x01ffff01ff000000, 0x01ffff01ff01ffff, 0x01ffff01ff0101ff,
-    0x01ffff010100ffff, 0x01ff00ffffff0000, 0x01ff00ffff010000, 0x01ff00ff00ffff01,
-    0x01ff0000ff0000ff, 0x01ff000000000000, 0x01ff00000001ff01, 0x01ff000001ffffff,
-    0x01ff000001010100, 0x01ff0001ffffff01, 0x01ff0001ff010001, 0x01ff000101ff0100,
-    0x01ff000101000001, 0x01ff0001010100ff, 0x01ff01ffff00ffff, 0x01ff01ff00010001,
-    0x01ff01ff01000000, 0x01ff01ff010101ff, 0x01ff0100ff000001, 0x01ff010000ffff00,
-    0x01ff010000000100, 0x01ff010001ff01ff, 0x01ff01000101ffff, 0x01ff0101ffff00ff,
-    0x01ff0101ffff0101, 0x01ff0101ff0101ff, 0x01ff010100010000, 0x0100ffff00ff00ff,
-    0x0100ffff00ff0001, 0x0100ffff00000100, 0x0100ffff0100ff00, 0x0100ff00ffff0000,
-    0x0100ff00ff00ffff, 0x0100ff00ff00ff01, 0x0100ff00ff000100, 0x0100ff00ff010000,
-    0x0100ff0000000000, 0x0100ff00000100ff, 0x0100ff0001ff0101, 0x0100ff0001010101,
-    0x0100ff0100ff00ff, 0x0100ff0100ff0001, 0x0100ff0100000100, 0x0100ff0100010001,
-    0x0100ff0101000000, 0x010000ffff00ff00, 0x010000ff0000ffff, 0x010000ff00000000,
-    0x010000ff010001ff, 0x010000ff01010001, 0x01000000ffffff00, 0x01000000ffff0101,
-    0x01000000ff000000, 0x01000000ff0100ff, 0x01000000ff010101, 0x0100000000ff0000,
-    0x010000000000ff00, 0x01000000000000ff, 0x0100000000000000, 0x0100000000000001,
-    0x0100000000000100, 0x0100000000010000, 0x0100000001000000, 0x0100000100000000,
-    0x01000001000101ff, 0x0100000101ffff01, 0x010001ffff000101, 0x010001ff00ff0100,
-    0x010001ff0000ff00, 0x010001ff000100ff, 0x010001ff01ffffff, 0x01000100ffff0000,
-    0x01000100ff0001ff, 0x0100010000000000, 0x010001000001ff00, 0x0100010001ff0000,
-    0x01000100010000ff, 0x0100010001000101, 0x01000101ff00ff01, 0x0100010100ff0100,
-    0x010001010000ffff, 0x0100010101010001, 0x0101ffffffff0101, 0x0101ffffff0001ff,
-    0x0101ffffff01ffff, 0x0101ffffff010101, 0x0101ffff00000000, 0x0101ffff0101ffff,
-    0x0101ffff010101ff, 0x0101ff00ff000000, 0x0101ff0000ff0100, 0x0101ff000000ff00,
-    0x0101ff0000010000, 0x0101ff00010000ff, 0x0101ff0001000001, 0x0101ff01ff010101,
-    0x0101ff0100000000, 0x0101ff010101ff00, 0x010100ffffff0000, 0x010100ffff010000,
-    0x010100ff00ff01ff, 0x010100ff000000ff, 0x010100ff00000101, 0x010100ff01ffff00,
-    0x01010000ffffff01, 0x01010000ff000100, 0x01010000ff01ff01, 0x0101000000000000,
-    0x01010000000100ff, 0x010100000101ff01, 0x01010001ffff0000, 0x01010001ff00ffff,
-    0x01010001ff010000, 0x0101000101ffffff, 0x0101000101ff01ff, 0x0101000101010101,
-    0x010101ffff01ffff, 0x010101ff00000000, 0x010101ff0001ff01, 0x010101ff0101ffff,
-    0x010101ff010101ff, 0x01010100ffffffff, 0x01010100ff000001, 0x010101000000ff00,
-    0x0101010001010000, 0x0101010100ff0001, 0x010101010001ff01, 0x010101010101ffff,
-};
-
-constexpr constant static uint8_t ksigns_iq2xs[128] = {
-      0, 129, 130,   3, 132,   5,   6, 135, 136,   9,  10, 139,  12, 141, 142,  15,
-    144,  17,  18, 147,  20, 149, 150,  23,  24, 153, 154,  27, 156,  29,  30, 159,
-    160,  33,  34, 163,  36, 165, 166,  39,  40, 169, 170,  43, 172,  45,  46, 175,
-     48, 177, 178,  51, 180,  53,  54, 183, 184,  57,  58, 187,  60, 189, 190,  63,
-    192,  65,  66, 195,  68, 197, 198,  71,  72, 201, 202,  75, 204,  77,  78, 207,
-     80, 209, 210,  83, 212,  85,  86, 215, 216,  89,  90, 219,  92, 221, 222,  95,
-     96, 225, 226,  99, 228, 101, 102, 231, 232, 105, 106, 235, 108, 237, 238, 111,
-    240, 113, 114, 243, 116, 245, 246, 119, 120, 249, 250, 123, 252, 125, 126, 255,
-};
-
-constexpr constant static uint8_t kmask_iq2xs[8] = {1, 2, 4, 8, 16, 32, 64, 128};
-
 void kernel_mul_mv_iq2_xxs_f32_impl(
         device const  void * src0,
         device const float * src1,
@@ -5039,48 +4338,53 @@ void kernel_mul_mv_iq1_s_f32_impl(
     device const block_iq1_s * x = (device const block_iq1_s *) src0 + ib_row + offset0;
     device const float       * y = (device const float       *) src1 + r1*ne10 + im*ne00*ne1;
 
-    float yl[16];
+    float yl[32];
     float sumf[N_DST]={0.f}, all_sum;
 
     const int nb32 = nb * (QK_K / 32);
 
-    const int ix = tiisg/2;
-    const int il = tiisg%2;
+    const int ix = tiisg;
 
-    device const float * y4 = y + 32 * ix + 16 * il;
+    device const float * y4 = y + 32 * ix;
 
-    for (int ib32 = ix; ib32 < nb32; ib32 += 16) {
+    for (int ib32 = ix; ib32 < nb32; ib32 += 32) {
 
-        for (int i = 0; i < 16; ++i) {
+        float sumy = 0;
+        for (int i = 0; i < 32; ++i) {
             yl[i] = y4[i];
+            sumy += yl[i];
         }
 
         const int ibl = ib32 / (QK_K / 32);
         const int ib  = ib32 % (QK_K / 32);
 
         device const block_iq1_s * xr = x + ibl;
-        device const uint8_t * qs = xr->qs + 4 * ib + 2 * il;
-        device const uint8_t * sc = xr->scales + 2 * ib + il;
-        device const half    * dh = &xr->d;
+        device const uint8_t  * qs = xr->qs + 4 * ib;
+        device const uint16_t * qh = xr->qh + ib;
+        device const half     * dh = &xr->d;
 
         for (int row = 0; row < N_DST; row++) {
 
-            constant int8_t * grid1 = (constant int8_t *)(iq1s_grid + (qs[0] | ((sc[0] & 0x08) << 5)));
-            constant int8_t * grid2 = (constant int8_t *)(iq1s_grid + (qs[1] | ((sc[0] & 0x80) << 1)));
+            constant uint8_t * grid1 = (constant uint8_t *)(iq1s_grid_gpu + (qs[0] | ((qh[0] << 8) & 0x700)));
+            constant uint8_t * grid2 = (constant uint8_t *)(iq1s_grid_gpu + (qs[1] | ((qh[0] << 5) & 0x700)));
+            constant uint8_t * grid3 = (constant uint8_t *)(iq1s_grid_gpu + (qs[2] | ((qh[0] << 2) & 0x700)));
+            constant uint8_t * grid4 = (constant uint8_t *)(iq1s_grid_gpu + (qs[3] | ((qh[0] >> 1) & 0x700)));
 
-            float2 sum = {0};
-            for (int j = 0; j < 8; ++j) {
-                sum[0] += yl[j+ 0] * grid1[j];
-                sum[1] += yl[j+ 8] * grid2[j];
+            float sum = 0;
+            for (int j = 0; j < 4; ++j) {
+                sum += yl[j+ 0] * (grid1[j] & 0xf) + yl[j+ 4] * (grid1[j] >> 4)
+                     + yl[j+ 8] * (grid2[j] & 0xf) + yl[j+12] * (grid2[j] >> 4)
+                     + yl[j+16] * (grid3[j] & 0xf) + yl[j+20] * (grid3[j] >> 4)
+                     + yl[j+24] * (grid4[j] & 0xf) + yl[j+28] * (grid4[j] >> 4);
             }
-            sumf[row] += (float)dh[0] * (sum[0] * (2*(sc[0] & 7) + 1) + sum[1] * (2*((sc[0] >> 4) & 7) + 1));
+            sumf[row] += (float)dh[0] * (sum - sumy) * (2*(qh[0] >> 12) + 1);
 
             dh += nb*sizeof(block_iq1_s)/2;
             qs += nb*sizeof(block_iq1_s);
-            sc += nb*sizeof(block_iq1_s);
+            qh += nb*sizeof(block_iq1_s)/2;
         }
 
-        y4 += 16 * 32;
+        y4 += 32 * 32;
     }
 
     for (int row = 0; row < N_DST; ++row) {
@@ -5767,16 +5071,19 @@ void dequantize_iq2_s(device const block_iq2_s * xb, short il, thread type4x4 &
 template <typename type4x4>
 void dequantize_iq1_s(device const block_iq1_s * xb, short il, thread type4x4 & reg) {
     // il is 0...15 for QK_K = 256 => index of block of 32 is il/2
+    const int ib32 = il/2;
+    il = il%2;
     const float d = xb->d;
-    device const uint8_t * qs = xb->qs + 2*il;
-    device const uint8_t * sc = xb->scales + il;
-    const float dl1 = d * (2*(sc[0] & 7) + 1);
-    const float dl2 = d * (2*((sc[0] >> 4) & 7) + 1);
-    constant int8_t * grid1 = (constant int8_t *)(iq1s_grid + (qs[0] | ((sc[0] & 0x08) << 5)));
-    constant int8_t * grid2 = (constant int8_t *)(iq1s_grid + (qs[1] | ((sc[0] & 0x80) << 1)));
-    for (int i = 0; i < 8; ++i) {
-        reg[i/4+0][i%4] = dl1 * grid1[i];
-        reg[i/4+2][i%4] = dl2 * grid2[i];
+    device const uint8_t  * qs = xb->qs + 4*ib32 + 2*il;
+    device const uint16_t * qh = xb->qh;
+    const float dl = d * (2*(qh[ib32] >> 12) + 1);
+    constant uint8_t * grid1 = (constant uint8_t *)(iq1s_grid_gpu + (qs[0] | (((qh[ib32] >> (6*il+0)) & 7) << 8)));
+    constant uint8_t * grid2 = (constant uint8_t *)(iq1s_grid_gpu + (qs[1] | (((qh[ib32] >> (6*il+3)) & 7) << 8)));
+    for (int i = 0; i < 4; ++i) {
+        reg[0][i] = dl * (grid1[i] & 0xf) - dl;
+        reg[1][i] = dl * (grid1[i] >>  4) - dl;
+        reg[2][i] = dl * (grid2[i] & 0xf) - dl;
+        reg[3][i] = dl * (grid2[i] >>  4) - dl;
     }
 }
 
@@ -6087,7 +5394,7 @@ template<typename block_q, short nl, void (*dequantize_func)(device const block_
 void kernel_mul_mm_id_impl(
         device const  uchar * src0,
         device const  uchar * src1,
-        thread        short * src1ids,
+        threadgroup   short * src1ids,
         device        float * dst,
         constant    int64_t & ne00,
         constant    int64_t & ne02,
@@ -6290,9 +5597,9 @@ kernel void kernel_mul_mm_id(
     tgpig.z = tgpig.z%(ne12*ne13);
 
     // row indices of src1 for expert id
-    int64_t _ne1 = 0;
-    short src1ids[512];
+    threadgroup short * src1ids = (threadgroup short *)(shared_memory + 8192);
 
+    int64_t _ne1 = 0;
     for (int64_t i1 = 0; i1 < ne1; i1++) {
         if (((device int32_t *) (ids + i1*nbi1))[idx] == id) {
             src1ids[_ne1++] = i1;
diff --git a/ggml-quants.c b/ggml-quants.c
index a8112a913..91da18b06 100644
--- a/ggml-quants.c
+++ b/ggml-quants.c
@@ -1,6 +1,9 @@
 #include "ggml-quants.h"
 #include "ggml-impl.h"
 
+#define GGML_COMMON_IMPL_C
+#include "ggml-common.h"
+
 #include <math.h>
 #include <string.h>
 #include <assert.h>
@@ -1702,16 +1705,6 @@ void quantize_row_q2_K(const float * restrict x, void * restrict vy, int k) {
     quantize_row_q2_K_reference(x, vy, k);
 }
 
-size_t ggml_quantize_q2_K(const float * restrict src, void * restrict dst, int n, int k, int64_t * restrict hist) {
-    (void)hist; // TODO: collect histograms
-
-    for (int j = 0; j < n; j += k) {
-        block_q2_K * restrict y = (block_q2_K *)dst + j/QK_K;
-        quantize_row_q2_K_reference(src + j, y, k);
-    }
-    return (n/QK_K*sizeof(block_q2_K));
-}
-
 static float make_qkx3_quants(int n, int nmax, const float * restrict x, const float * restrict weights,
         uint8_t * restrict L, float * restrict the_min, uint8_t * restrict Laux,
         float rmin, float rdelta, int nstep, bool use_mad) {
@@ -1964,8 +1957,7 @@ static void quantize_row_q2_K_impl(const float * restrict x, block_q2_K * restri
     }
 }
 
-size_t quantize_q2_K(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) {
-    (void)hist;
+size_t quantize_q2_K(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) {
     size_t row_size = ggml_row_size(GGML_TYPE_Q2_K, n_per_row);
     if (!quant_weights) {
         quantize_row_q2_K_reference(src, dst, nrow*n_per_row);
@@ -2184,16 +2176,6 @@ void quantize_row_q3_K(const float * restrict x, void * restrict vy, int k) {
     quantize_row_q3_K_reference(x, vy, k);
 }
 
-size_t ggml_quantize_q3_K(const float * restrict src, void * restrict dst, int n, int k, int64_t * restrict hist) {
-    (void)hist; // TODO: collect histograms
-
-    for (int j = 0; j < n; j += k) {
-        block_q3_K * restrict y = (block_q3_K *)dst + j/QK_K;
-        quantize_row_q3_K_reference(src + j, y, k);
-    }
-    return (n/QK_K*sizeof(block_q3_K));
-}
-
 static void quantize_row_q3_K_impl(const float * restrict x, block_q3_K * restrict y, int n_per_row, const float * restrict quant_weights) {
 #if QK_K != 256
     (void)quant_weights;
@@ -2283,8 +2265,7 @@ static void quantize_row_q3_K_impl(const float * restrict x, block_q3_K * restri
 #endif
 }
 
-size_t quantize_q3_K(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) {
-    (void)hist;
+size_t quantize_q3_K(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) {
     size_t row_size = ggml_row_size(GGML_TYPE_Q3_K, n_per_row);
     if (!quant_weights) {
         quantize_row_q3_K_reference(src, dst, nrow*n_per_row);
@@ -2454,17 +2435,6 @@ void quantize_row_q4_K(const float * restrict x, void * restrict vy, int k) {
     quantize_row_q4_K_reference(x, y, k);
 }
 
-size_t ggml_quantize_q4_K(const float * restrict src, void * restrict dst, int n, int k, int64_t * restrict hist) {
-    assert(k % QK_K == 0);
-    (void)hist; // TODO: collect histograms
-
-    for (int j = 0; j < n; j += k) {
-        block_q4_K * restrict y = (block_q4_K *)dst + j/QK_K;
-        quantize_row_q4_K_reference(src + j, y, k);
-    }
-    return (n/QK_K*sizeof(block_q4_K));
-}
-
 static void quantize_row_q4_K_impl(const float * restrict x, block_q4_K * restrict y, int n_per_row, const float * quant_weights) {
 #if QK_K != 256
     (void)quant_weights;
@@ -2543,8 +2513,7 @@ static void quantize_row_q4_K_impl(const float * restrict x, block_q4_K * restri
 #endif
 }
 
-size_t quantize_q4_K(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) {
-    (void)hist;
+size_t quantize_q4_K(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) {
     size_t row_size = ggml_row_size(GGML_TYPE_Q4_K, n_per_row);
     if (!quant_weights) {
         quantize_row_q4_K_reference(src, dst, nrow*n_per_row);
@@ -2755,17 +2724,6 @@ void quantize_row_q5_K(const float * restrict x, void * restrict vy, int k) {
     quantize_row_q5_K_reference(x, y, k);
 }
 
-size_t ggml_quantize_q5_K(const float * restrict src, void * restrict dst, int n, int k, int64_t * restrict hist) {
-    assert(k % QK_K == 0);
-    (void)hist; // TODO: collect histograms
-
-    for (int j = 0; j < n; j += k) {
-        block_q5_K * restrict y = (block_q5_K *)dst + j/QK_K;
-        quantize_row_q5_K_reference(src + j, y, k);
-    }
-    return (n/QK_K*sizeof(block_q5_K));
-}
-
 static void quantize_row_q5_K_impl(const float * restrict x, block_q5_K * restrict y, int n_per_row, const float * quant_weights) {
 #if QK_K != 256
     (void)quant_weights;
@@ -2864,8 +2822,7 @@ static void quantize_row_q5_K_impl(const float * restrict x, block_q5_K * restri
 #endif
 }
 
-size_t quantize_q5_K(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) {
-    (void)hist;
+size_t quantize_q5_K(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) {
     size_t row_size = ggml_row_size(GGML_TYPE_Q5_K, n_per_row);
     if (!quant_weights) {
         quantize_row_q5_K_reference(src, dst, nrow*n_per_row);
@@ -3018,17 +2975,6 @@ void quantize_row_q6_K(const float * restrict x, void * restrict vy, int k) {
     quantize_row_q6_K_reference(x, y, k);
 }
 
-size_t ggml_quantize_q6_K(const float * src, void * dst, int n, int k, int64_t * hist) {
-    assert(k % QK_K == 0);
-    (void)hist; // TODO: collect histograms
-
-    for (int j = 0; j < n; j += k) {
-        block_q6_K * restrict y = (block_q6_K *)dst + j/QK_K;
-        quantize_row_q6_K_reference(src + j, y, k);
-    }
-    return (n/QK_K*sizeof(block_q6_K));
-}
-
 static void quantize_row_q6_K_impl(const float * restrict x, block_q6_K * restrict y, int n_per_row, const float * quant_weights) {
 #if QK_K != 256
     (void)quant_weights;
@@ -3118,8 +3064,7 @@ static void quantize_row_q6_K_impl(const float * restrict x, block_q6_K * restri
 #endif
 }
 
-size_t quantize_q6_K(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) {
-    (void)hist;
+size_t quantize_q6_K(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) {
     size_t row_size = ggml_row_size(GGML_TYPE_Q6_K, n_per_row);
     if (!quant_weights) {
         quantize_row_q6_K_reference(src, dst, nrow*n_per_row);
@@ -3163,9 +3108,10 @@ static void quantize_row_q4_0_impl(const float * restrict x, block_q4_0 * restri
     }
 }
 
-size_t quantize_q4_0(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) {
+size_t quantize_q4_0(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) {
     if (!quant_weights) {
-        return ggml_quantize_q4_0(src, dst, nrow*n_per_row, n_per_row, hist);
+        quantize_row_q4_0_reference(src, dst, nrow*n_per_row);
+        return nrow * ggml_row_size(GGML_TYPE_Q4_0, n_per_row);
     }
     size_t row_size = ggml_row_size(GGML_TYPE_Q4_0, n_per_row);
     char * qrow = (char *)dst;
@@ -3207,9 +3153,10 @@ static void quantize_row_q4_1_impl(const float * restrict x, block_q4_1 * restri
     }
 }
 
-size_t quantize_q4_1(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) {
+size_t quantize_q4_1(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) {
     if (!quant_weights) {
-        return ggml_quantize_q4_1(src, dst, nrow*n_per_row, n_per_row, hist);
+        quantize_row_q4_1_reference(src, dst, nrow*n_per_row);
+        return nrow * ggml_row_size(GGML_TYPE_Q4_1, n_per_row);
     }
     size_t row_size = ggml_row_size(GGML_TYPE_Q4_1, n_per_row);
     char * qrow = (char *)dst;
@@ -3260,9 +3207,10 @@ static void quantize_row_q5_0_impl(const float * restrict x, block_q5_0 * restri
     }
 }
 
-size_t quantize_q5_0(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) {
+size_t quantize_q5_0(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) {
     if (!quant_weights) {
-        return ggml_quantize_q5_0(src, dst, nrow*n_per_row, n_per_row, hist);
+        quantize_row_q5_0_reference(src, dst, nrow*n_per_row);
+        return nrow * ggml_row_size(GGML_TYPE_Q5_0, n_per_row);
     }
     size_t row_size = ggml_row_size(GGML_TYPE_Q5_0, n_per_row);
     char * qrow = (char *)dst;
@@ -3312,9 +3260,10 @@ static void quantize_row_q5_1_impl(const float * restrict x, block_q5_1 * restri
     }
 }
 
-size_t quantize_q5_1(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) {
+size_t quantize_q5_1(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) {
     if (!quant_weights) {
-        return ggml_quantize_q5_1(src, dst, nrow*n_per_row, n_per_row, hist);
+        quantize_row_q5_1_reference(src, dst, nrow*n_per_row);
+        return nrow * ggml_row_size(GGML_TYPE_Q5_1, n_per_row);
     }
     size_t row_size = ggml_row_size(GGML_TYPE_Q5_1, n_per_row);
     char * qrow = (char *)dst;
@@ -3326,713 +3275,15 @@ size_t quantize_q5_1(const float * src, void * dst, int nrow, int n_per_row, int
     return nrow * row_size;
 }
 
+size_t quantize_q8_0(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) {
+    (void)quant_weights; // not used
+    const size_t row_size = ggml_row_size(GGML_TYPE_Q8_0, n_per_row);
+    quantize_row_q8_0_reference(src, dst, nrow*n_per_row);
+    return nrow * row_size;
+}
+
 // ====================== "True" 2-bit (de)-quantization
 
-static const  uint64_t iq2xxs_grid[256] = {
-    0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08,
-    0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x08080808082b0808,
-    0x08080808082b082b, 0x08080808082b2b08, 0x08080808082b2b2b, 0x0808080819080819,
-    0x0808080819081908, 0x0808080819190808, 0x0808080819192b08, 0x08080808192b0819,
-    0x08080808192b1908, 0x080808082b080808, 0x080808082b08082b, 0x080808082b082b2b,
-    0x080808082b2b082b, 0x0808081908080819, 0x0808081908081908, 0x0808081908190808,
-    0x0808081908191919, 0x0808081919080808, 0x080808192b081908, 0x080808192b192b08,
-    0x0808082b08080808, 0x0808082b0808082b, 0x0808082b082b082b, 0x0808082b2b08082b,
-    0x0808190808080819, 0x0808190808081908, 0x0808190808190808, 0x08081908082b0819,
-    0x08081908082b1908, 0x0808190819080808, 0x080819081908082b, 0x0808190819082b08,
-    0x08081908192b0808, 0x080819082b080819, 0x080819082b081908, 0x080819082b190808,
-    0x080819082b2b1908, 0x0808191908080808, 0x080819190808082b, 0x0808191908082b08,
-    0x08081919082b0808, 0x080819191908192b, 0x08081919192b2b19, 0x080819192b080808,
-    0x080819192b190819, 0x0808192b08082b19, 0x0808192b08190808, 0x0808192b19080808,
-    0x0808192b2b081908, 0x0808192b2b2b1908, 0x08082b0808080808, 0x08082b0808081919,
-    0x08082b0808082b08, 0x08082b0808191908, 0x08082b08082b2b08, 0x08082b0819080819,
-    0x08082b0819081908, 0x08082b0819190808, 0x08082b081919082b, 0x08082b082b082b08,
-    0x08082b1908081908, 0x08082b1919080808, 0x08082b2b0808082b, 0x08082b2b08191908,
-    0x0819080808080819, 0x0819080808081908, 0x0819080808190808, 0x08190808082b0819,
-    0x0819080819080808, 0x08190808192b0808, 0x081908082b081908, 0x081908082b190808,
-    0x081908082b191919, 0x0819081908080808, 0x0819081908082b08, 0x08190819082b0808,
-    0x0819081919190808, 0x0819081919192b2b, 0x081908192b080808, 0x0819082b082b1908,
-    0x0819082b19081919, 0x0819190808080808, 0x0819190808082b08, 0x08191908082b0808,
-    0x08191908082b1919, 0x0819190819082b19, 0x081919082b080808, 0x0819191908192b08,
-    0x08191919192b082b, 0x0819192b08080808, 0x0819192b0819192b, 0x08192b0808080819,
-    0x08192b0808081908, 0x08192b0808190808, 0x08192b0819080808, 0x08192b082b080819,
-    0x08192b1908080808, 0x08192b1908081919, 0x08192b192b2b0808, 0x08192b2b19190819,
-    0x082b080808080808, 0x082b08080808082b, 0x082b080808082b2b, 0x082b080819081908,
-    0x082b0808192b0819, 0x082b08082b080808, 0x082b08082b08082b, 0x082b0819082b2b19,
-    0x082b081919082b08, 0x082b082b08080808, 0x082b082b0808082b, 0x082b190808080819,
-    0x082b190808081908, 0x082b190808190808, 0x082b190819080808, 0x082b19081919192b,
-    0x082b191908080808, 0x082b191919080819, 0x082b1919192b1908, 0x082b192b2b190808,
-    0x082b2b0808082b08, 0x082b2b08082b0808, 0x082b2b082b191908, 0x082b2b2b19081908,
-    0x1908080808080819, 0x1908080808081908, 0x1908080808190808, 0x1908080808192b08,
-    0x19080808082b0819, 0x19080808082b1908, 0x1908080819080808, 0x1908080819082b08,
-    0x190808081919192b, 0x19080808192b0808, 0x190808082b080819, 0x190808082b081908,
-    0x190808082b190808, 0x1908081908080808, 0x19080819082b0808, 0x19080819192b0819,
-    0x190808192b080808, 0x190808192b081919, 0x1908082b08080819, 0x1908082b08190808,
-    0x1908082b19082b08, 0x1908082b1919192b, 0x1908082b192b2b08, 0x1908190808080808,
-    0x1908190808082b08, 0x19081908082b0808, 0x190819082b080808, 0x190819082b192b19,
-    0x190819190819082b, 0x19081919082b1908, 0x1908192b08080808, 0x19082b0808080819,
-    0x19082b0808081908, 0x19082b0808190808, 0x19082b0819080808, 0x19082b0819081919,
-    0x19082b1908080808, 0x19082b1919192b08, 0x19082b19192b0819, 0x19082b192b08082b,
-    0x19082b2b19081919, 0x19082b2b2b190808, 0x1919080808080808, 0x1919080808082b08,
-    0x1919080808190819, 0x1919080808192b19, 0x19190808082b0808, 0x191908082b080808,
-    0x191908082b082b08, 0x1919081908081908, 0x191908191908082b, 0x191908192b2b1908,
-    0x1919082b2b190819, 0x191919082b190808, 0x191919082b19082b, 0x1919191908082b2b,
-    0x1919192b08080819, 0x1919192b19191908, 0x19192b0808080808, 0x19192b0808190819,
-    0x19192b0808192b19, 0x19192b08192b1908, 0x19192b1919080808, 0x19192b2b08082b08,
-    0x192b080808081908, 0x192b080808190808, 0x192b080819080808, 0x192b0808192b2b08,
-    0x192b081908080808, 0x192b081919191919, 0x192b082b08192b08, 0x192b082b192b0808,
-    0x192b190808080808, 0x192b190808081919, 0x192b191908190808, 0x192b19190819082b,
-    0x192b19192b081908, 0x192b2b081908082b, 0x2b08080808080808, 0x2b0808080808082b,
-    0x2b08080808082b2b, 0x2b08080819080819, 0x2b0808082b08082b, 0x2b08081908081908,
-    0x2b08081908192b08, 0x2b08081919080808, 0x2b08082b08190819, 0x2b08190808080819,
-    0x2b08190808081908, 0x2b08190808190808, 0x2b08190808191919, 0x2b08190819080808,
-    0x2b081908192b0808, 0x2b08191908080808, 0x2b0819191908192b, 0x2b0819192b191908,
-    0x2b08192b08082b19, 0x2b08192b19080808, 0x2b08192b192b0808, 0x2b082b080808082b,
-    0x2b082b1908081908, 0x2b082b2b08190819, 0x2b19080808081908, 0x2b19080808190808,
-    0x2b190808082b1908, 0x2b19080819080808, 0x2b1908082b2b0819, 0x2b1908190819192b,
-    0x2b1908192b080808, 0x2b19082b19081919, 0x2b19190808080808, 0x2b191908082b082b,
-    0x2b19190819081908, 0x2b19191919190819, 0x2b192b082b080819, 0x2b192b19082b0808,
-    0x2b2b08080808082b, 0x2b2b080819190808, 0x2b2b08082b081919, 0x2b2b081908082b19,
-    0x2b2b082b08080808, 0x2b2b190808192b08, 0x2b2b2b0819190808, 0x2b2b2b1908081908,
-};
-
-static const uint64_t iq2xs_grid[512] = {
-    0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08,
-    0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x080808080819192b,
-    0x0808080808192b19, 0x08080808082b0808, 0x08080808082b082b, 0x08080808082b1919,
-    0x08080808082b2b08, 0x0808080819080819, 0x0808080819081908, 0x080808081908192b,
-    0x0808080819082b19, 0x0808080819190808, 0x080808081919082b, 0x0808080819191919,
-    0x0808080819192b08, 0x08080808192b0819, 0x08080808192b1908, 0x080808082b080808,
-    0x080808082b08082b, 0x080808082b081919, 0x080808082b082b08, 0x080808082b190819,
-    0x080808082b191908, 0x080808082b192b19, 0x080808082b2b0808, 0x0808081908080819,
-    0x0808081908081908, 0x080808190808192b, 0x0808081908082b19, 0x0808081908190808,
-    0x080808190819082b, 0x0808081908191919, 0x0808081908192b08, 0x0808081908192b2b,
-    0x08080819082b0819, 0x08080819082b1908, 0x0808081919080808, 0x080808191908082b,
-    0x0808081919081919, 0x0808081919082b08, 0x0808081919190819, 0x0808081919191908,
-    0x08080819192b0808, 0x08080819192b2b08, 0x080808192b080819, 0x080808192b081908,
-    0x080808192b190808, 0x0808082b08080808, 0x0808082b0808082b, 0x0808082b08081919,
-    0x0808082b08082b08, 0x0808082b08190819, 0x0808082b08191908, 0x0808082b082b0808,
-    0x0808082b19080819, 0x0808082b19081908, 0x0808082b19190808, 0x0808082b19191919,
-    0x0808082b2b080808, 0x0808082b2b082b2b, 0x0808190808080819, 0x0808190808081908,
-    0x080819080808192b, 0x0808190808082b19, 0x0808190808190808, 0x080819080819082b,
-    0x0808190808191919, 0x0808190808192b08, 0x08081908082b0819, 0x08081908082b1908,
-    0x0808190819080808, 0x080819081908082b, 0x0808190819081919, 0x0808190819082b08,
-    0x0808190819190819, 0x0808190819191908, 0x080819081919192b, 0x08081908192b0808,
-    0x080819082b080819, 0x080819082b081908, 0x080819082b190808, 0x0808191908080808,
-    0x080819190808082b, 0x0808191908081919, 0x0808191908082b08, 0x0808191908190819,
-    0x0808191908191908, 0x08081919082b0808, 0x0808191919080819, 0x0808191919081908,
-    0x0808191919190808, 0x08081919192b0819, 0x080819192b080808, 0x0808192b08080819,
-    0x0808192b08081908, 0x0808192b08190808, 0x0808192b082b192b, 0x0808192b19080808,
-    0x0808192b1908082b, 0x0808192b2b081908, 0x08082b0808080808, 0x08082b080808082b,
-    0x08082b0808081919, 0x08082b0808082b08, 0x08082b0808082b2b, 0x08082b0808190819,
-    0x08082b0808191908, 0x08082b08082b0808, 0x08082b08082b1919, 0x08082b0819080819,
-    0x08082b0819081908, 0x08082b0819190808, 0x08082b0819192b08, 0x08082b082b080808,
-    0x08082b082b2b0808, 0x08082b082b2b2b2b, 0x08082b1908080819, 0x08082b1908081908,
-    0x08082b1908190808, 0x08082b1919080808, 0x08082b192b080819, 0x08082b192b082b19,
-    0x08082b2b08080808, 0x08082b2b082b0808, 0x08082b2b082b2b08, 0x08082b2b2b19192b,
-    0x08082b2b2b2b0808, 0x0819080808080819, 0x0819080808081908, 0x081908080808192b,
-    0x0819080808082b19, 0x0819080808190808, 0x081908080819082b, 0x0819080808191919,
-    0x0819080808192b08, 0x08190808082b0819, 0x08190808082b1908, 0x0819080819080808,
-    0x081908081908082b, 0x0819080819081919, 0x0819080819082b08, 0x0819080819190819,
-    0x0819080819191908, 0x08190808192b0808, 0x08190808192b2b2b, 0x081908082b080819,
-    0x081908082b081908, 0x081908082b190808, 0x0819081908080808, 0x081908190808082b,
-    0x0819081908081919, 0x0819081908082b08, 0x0819081908190819, 0x0819081908191908,
-    0x08190819082b0808, 0x0819081919080819, 0x0819081919081908, 0x0819081919190808,
-    0x081908192b080808, 0x081908192b191908, 0x081908192b19192b, 0x0819082b08080819,
-    0x0819082b08081908, 0x0819082b0808192b, 0x0819082b08190808, 0x0819082b19080808,
-    0x0819082b192b0808, 0x0819190808080808, 0x081919080808082b, 0x0819190808081919,
-    0x0819190808082b08, 0x0819190808190819, 0x0819190808191908, 0x08191908082b0808,
-    0x0819190819080819, 0x0819190819081908, 0x0819190819082b19, 0x0819190819190808,
-    0x08191908192b1908, 0x081919082b080808, 0x0819191908080819, 0x0819191908081908,
-    0x0819191908190808, 0x0819191919080808, 0x0819192b08080808, 0x0819192b08191908,
-    0x0819192b19082b19, 0x08192b0808080819, 0x08192b0808081908, 0x08192b0808190808,
-    0x08192b080819082b, 0x08192b0819080808, 0x08192b0819191908, 0x08192b082b08192b,
-    0x08192b1908080808, 0x08192b1908081919, 0x08192b19192b192b, 0x08192b2b19190819,
-    0x08192b2b2b2b2b19, 0x082b080808080808, 0x082b08080808082b, 0x082b080808081919,
-    0x082b080808082b08, 0x082b080808082b2b, 0x082b080808190819, 0x082b080808191908,
-    0x082b0808082b0808, 0x082b080819080819, 0x082b080819081908, 0x082b080819190808,
-    0x082b08082b080808, 0x082b08082b2b0808, 0x082b081908080819, 0x082b081908081908,
-    0x082b081908190808, 0x082b081919080808, 0x082b081919082b08, 0x082b0819192b1919,
-    0x082b082b08080808, 0x082b082b082b082b, 0x082b082b2b080808, 0x082b082b2b2b2b08,
-    0x082b190808080819, 0x082b190808081908, 0x082b190808190808, 0x082b1908082b2b19,
-    0x082b190819080808, 0x082b191908080808, 0x082b191919080819, 0x082b19191919082b,
-    0x082b19192b192b19, 0x082b192b08080819, 0x082b192b08192b2b, 0x082b192b2b2b192b,
-    0x082b2b0808080808, 0x082b2b0808082b08, 0x082b2b0808082b2b, 0x082b2b08082b0808,
-    0x082b2b0819191919, 0x082b2b082b082b08, 0x082b2b082b2b082b, 0x082b2b19192b2b08,
-    0x082b2b192b190808, 0x082b2b2b08082b08, 0x082b2b2b082b0808, 0x082b2b2b2b08082b,
-    0x082b2b2b2b082b08, 0x082b2b2b2b082b2b, 0x1908080808080819, 0x1908080808081908,
-    0x190808080808192b, 0x1908080808082b19, 0x1908080808190808, 0x190808080819082b,
-    0x1908080808191919, 0x1908080808192b08, 0x19080808082b0819, 0x19080808082b1908,
-    0x1908080819080808, 0x190808081908082b, 0x1908080819081919, 0x1908080819082b08,
-    0x1908080819082b2b, 0x1908080819190819, 0x1908080819191908, 0x19080808192b0808,
-    0x19080808192b1919, 0x190808082b080819, 0x190808082b081908, 0x190808082b190808,
-    0x1908081908080808, 0x190808190808082b, 0x1908081908081919, 0x1908081908082b08,
-    0x1908081908190819, 0x1908081908191908, 0x19080819082b0808, 0x1908081919080819,
-    0x1908081919081908, 0x1908081919190808, 0x190808192b080808, 0x190808192b081919,
-    0x190808192b2b082b, 0x1908082b08080819, 0x1908082b08081908, 0x1908082b08190808,
-    0x1908082b0819082b, 0x1908082b082b2b19, 0x1908082b19080808, 0x1908190808080808,
-    0x190819080808082b, 0x1908190808081919, 0x1908190808082b08, 0x1908190808190819,
-    0x1908190808191908, 0x1908190808192b19, 0x19081908082b0808, 0x1908190819080819,
-    0x1908190819081908, 0x1908190819190808, 0x190819082b080808, 0x190819082b191908,
-    0x1908191908080819, 0x1908191908081908, 0x1908191908190808, 0x19081919082b1908,
-    0x1908191919080808, 0x190819192b192b2b, 0x1908192b08080808, 0x1908192b08082b2b,
-    0x1908192b19081908, 0x1908192b19190808, 0x19082b0808080819, 0x19082b0808081908,
-    0x19082b0808190808, 0x19082b0819080808, 0x19082b0819081919, 0x19082b0819191908,
-    0x19082b08192b082b, 0x19082b1908080808, 0x19082b1908190819, 0x19082b1919081908,
-    0x19082b1919190808, 0x19082b19192b2b19, 0x19082b2b08081908, 0x1919080808080808,
-    0x191908080808082b, 0x1919080808081919, 0x1919080808082b08, 0x1919080808190819,
-    0x1919080808191908, 0x19190808082b0808, 0x19190808082b2b08, 0x1919080819080819,
-    0x1919080819081908, 0x1919080819190808, 0x191908082b080808, 0x1919081908080819,
-    0x1919081908081908, 0x1919081908190808, 0x1919081908191919, 0x1919081919080808,
-    0x191908191908082b, 0x1919082b08080808, 0x1919082b19081908, 0x1919082b2b2b2b2b,
-    0x1919190808080819, 0x1919190808081908, 0x1919190808190808, 0x19191908082b0819,
-    0x1919190819080808, 0x19191908192b0808, 0x191919082b080819, 0x191919082b2b0819,
-    0x1919191908080808, 0x1919191908082b08, 0x191919192b080808, 0x191919192b082b08,
-    0x1919192b082b0819, 0x1919192b192b2b08, 0x1919192b2b2b0819, 0x19192b0808080808,
-    0x19192b0808191908, 0x19192b0819080819, 0x19192b0819190808, 0x19192b082b192b19,
-    0x19192b1908192b2b, 0x19192b1919080808, 0x19192b191908082b, 0x19192b2b2b081919,
-    0x192b080808080819, 0x192b080808081908, 0x192b080808190808, 0x192b080819080808,
-    0x192b080819191908, 0x192b0808192b082b, 0x192b08082b08192b, 0x192b08082b2b2b19,
-    0x192b081908080808, 0x192b082b082b1908, 0x192b082b19082b2b, 0x192b082b2b19082b,
-    0x192b190808080808, 0x192b19080819192b, 0x192b191908190808, 0x192b191919080808,
-    0x192b191919081919, 0x192b19192b2b1908, 0x192b2b0808080819, 0x192b2b08192b2b2b,
-    0x192b2b19082b1919, 0x192b2b2b0808192b, 0x192b2b2b19191908, 0x192b2b2b192b082b,
-    0x2b08080808080808, 0x2b0808080808082b, 0x2b08080808081919, 0x2b08080808082b08,
-    0x2b08080808190819, 0x2b08080808191908, 0x2b080808082b0808, 0x2b080808082b2b2b,
-    0x2b08080819080819, 0x2b08080819081908, 0x2b08080819190808, 0x2b0808082b080808,
-    0x2b0808082b08082b, 0x2b0808082b2b2b08, 0x2b0808082b2b2b2b, 0x2b08081908080819,
-    0x2b08081908081908, 0x2b0808190808192b, 0x2b08081908190808, 0x2b08081919080808,
-    0x2b08081919190819, 0x2b08081919192b19, 0x2b08082b08080808, 0x2b08082b082b0808,
-    0x2b08082b2b080808, 0x2b08082b2b08082b, 0x2b08082b2b2b0808, 0x2b08082b2b2b2b08,
-    0x2b08190808080819, 0x2b08190808081908, 0x2b08190808190808, 0x2b0819080819082b,
-    0x2b08190808191919, 0x2b08190819080808, 0x2b081908192b0808, 0x2b0819082b082b19,
-    0x2b08191908080808, 0x2b08191919081908, 0x2b0819192b2b1919, 0x2b08192b08192b08,
-    0x2b08192b192b2b2b, 0x2b082b0808080808, 0x2b082b0808082b08, 0x2b082b08082b1919,
-    0x2b082b0819192b2b, 0x2b082b082b080808, 0x2b082b082b08082b, 0x2b082b082b2b2b08,
-    0x2b082b190808192b, 0x2b082b2b082b082b, 0x2b082b2b2b080808, 0x2b082b2b2b082b08,
-    0x2b082b2b2b19192b, 0x2b082b2b2b2b2b08, 0x2b19080808080819, 0x2b19080808081908,
-    0x2b19080808190808, 0x2b19080819080808, 0x2b1908081919192b, 0x2b1908082b081908,
-    0x2b19081908080808, 0x2b190819082b082b, 0x2b190819192b1908, 0x2b19082b1919192b,
-    0x2b19082b2b082b19, 0x2b19190808080808, 0x2b19190808081919, 0x2b19190819081908,
-    0x2b19190819190808, 0x2b19190819192b08, 0x2b191919082b2b19, 0x2b1919192b190808,
-    0x2b1919192b19082b, 0x2b19192b19080819, 0x2b192b0819190819, 0x2b192b082b2b192b,
-    0x2b192b1919082b19, 0x2b192b2b08191919, 0x2b192b2b192b0808, 0x2b2b080808080808,
-    0x2b2b08080808082b, 0x2b2b080808082b08, 0x2b2b080808082b2b, 0x2b2b0808082b0808,
-    0x2b2b0808082b2b2b, 0x2b2b08082b2b0808, 0x2b2b081919190819, 0x2b2b081919192b19,
-    0x2b2b08192b2b192b, 0x2b2b082b08080808, 0x2b2b082b0808082b, 0x2b2b082b08082b08,
-    0x2b2b082b082b2b2b, 0x2b2b082b2b080808, 0x2b2b082b2b2b0808, 0x2b2b190819080808,
-    0x2b2b19082b191919, 0x2b2b192b192b1919, 0x2b2b192b2b192b08, 0x2b2b2b0808082b2b,
-    0x2b2b2b08082b0808, 0x2b2b2b08082b082b, 0x2b2b2b08082b2b08, 0x2b2b2b082b2b0808,
-    0x2b2b2b082b2b2b08, 0x2b2b2b1908081908, 0x2b2b2b192b081908, 0x2b2b2b192b08192b,
-    0x2b2b2b2b082b2b08, 0x2b2b2b2b082b2b2b, 0x2b2b2b2b2b190819, 0x2b2b2b2b2b2b2b2b,
-};
-
-static const uint64_t iq2s_grid[1024] = {
-    0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08,
-    0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x080808080819192b,
-    0x0808080808192b19, 0x08080808082b0808, 0x08080808082b082b, 0x08080808082b1919,
-    0x08080808082b2b08, 0x0808080819080819, 0x0808080819081908, 0x080808081908192b,
-    0x0808080819082b19, 0x0808080819190808, 0x080808081919082b, 0x0808080819191919,
-    0x0808080819192b08, 0x08080808192b0819, 0x08080808192b1908, 0x08080808192b192b,
-    0x08080808192b2b19, 0x080808082b080808, 0x080808082b08082b, 0x080808082b081919,
-    0x080808082b082b08, 0x080808082b190819, 0x080808082b191908, 0x080808082b2b0808,
-    0x080808082b2b1919, 0x080808082b2b2b2b, 0x0808081908080819, 0x0808081908081908,
-    0x080808190808192b, 0x0808081908082b19, 0x0808081908190808, 0x080808190819082b,
-    0x0808081908191919, 0x0808081908192b08, 0x08080819082b0819, 0x08080819082b1908,
-    0x0808081919080808, 0x080808191908082b, 0x0808081919081919, 0x0808081919082b08,
-    0x0808081919190819, 0x0808081919191908, 0x080808191919192b, 0x0808081919192b19,
-    0x08080819192b0808, 0x08080819192b1919, 0x08080819192b2b08, 0x080808192b080819,
-    0x080808192b081908, 0x080808192b190808, 0x080808192b19082b, 0x080808192b191919,
-    0x080808192b2b0819, 0x080808192b2b1908, 0x0808082b08080808, 0x0808082b0808082b,
-    0x0808082b08081919, 0x0808082b08082b08, 0x0808082b08190819, 0x0808082b08191908,
-    0x0808082b082b0808, 0x0808082b082b2b2b, 0x0808082b19080819, 0x0808082b19081908,
-    0x0808082b1908192b, 0x0808082b19082b19, 0x0808082b19190808, 0x0808082b19191919,
-    0x0808082b2b080808, 0x0808082b2b081919, 0x0808082b2b082b2b, 0x0808082b2b191908,
-    0x0808082b2b2b082b, 0x0808190808080819, 0x0808190808081908, 0x080819080808192b,
-    0x0808190808082b19, 0x0808190808190808, 0x080819080819082b, 0x0808190808191919,
-    0x0808190808192b08, 0x08081908082b0819, 0x08081908082b1908, 0x08081908082b192b,
-    0x08081908082b2b19, 0x0808190819080808, 0x080819081908082b, 0x0808190819081919,
-    0x0808190819082b08, 0x0808190819082b2b, 0x0808190819190819, 0x0808190819191908,
-    0x080819081919192b, 0x0808190819192b19, 0x08081908192b0808, 0x08081908192b082b,
-    0x08081908192b1919, 0x080819082b080819, 0x080819082b081908, 0x080819082b08192b,
-    0x080819082b082b19, 0x080819082b190808, 0x080819082b191919, 0x080819082b192b08,
-    0x080819082b2b0819, 0x080819082b2b1908, 0x0808191908080808, 0x080819190808082b,
-    0x0808191908081919, 0x0808191908082b08, 0x0808191908082b2b, 0x0808191908190819,
-    0x0808191908191908, 0x080819190819192b, 0x0808191908192b19, 0x08081919082b0808,
-    0x08081919082b1919, 0x08081919082b2b08, 0x0808191919080819, 0x0808191919081908,
-    0x080819191908192b, 0x0808191919082b19, 0x0808191919190808, 0x080819191919082b,
-    0x0808191919191919, 0x0808191919192b08, 0x08081919192b0819, 0x08081919192b1908,
-    0x080819192b080808, 0x080819192b08082b, 0x080819192b081919, 0x080819192b082b08,
-    0x080819192b190819, 0x080819192b191908, 0x080819192b2b0808, 0x0808192b08080819,
-    0x0808192b08081908, 0x0808192b0808192b, 0x0808192b08082b19, 0x0808192b08190808,
-    0x0808192b08191919, 0x0808192b19080808, 0x0808192b19081919, 0x0808192b19082b08,
-    0x0808192b19190819, 0x0808192b19191908, 0x0808192b192b0808, 0x0808192b2b080819,
-    0x0808192b2b081908, 0x0808192b2b190808, 0x08082b0808080808, 0x08082b080808082b,
-    0x08082b0808081919, 0x08082b0808082b08, 0x08082b0808190819, 0x08082b0808191908,
-    0x08082b080819192b, 0x08082b0808192b19, 0x08082b08082b0808, 0x08082b08082b1919,
-    0x08082b08082b2b2b, 0x08082b0819080819, 0x08082b0819081908, 0x08082b081908192b,
-    0x08082b0819082b19, 0x08082b0819190808, 0x08082b081919082b, 0x08082b0819191919,
-    0x08082b0819192b08, 0x08082b08192b0819, 0x08082b08192b1908, 0x08082b082b080808,
-    0x08082b082b081919, 0x08082b082b191908, 0x08082b082b2b2b2b, 0x08082b1908080819,
-    0x08082b1908081908, 0x08082b1908190808, 0x08082b190819082b, 0x08082b1908191919,
-    0x08082b1908192b08, 0x08082b19082b0819, 0x08082b1919080808, 0x08082b1919081919,
-    0x08082b1919082b08, 0x08082b1919190819, 0x08082b1919191908, 0x08082b19192b0808,
-    0x08082b192b080819, 0x08082b192b190808, 0x08082b2b08080808, 0x08082b2b08190819,
-    0x08082b2b08191908, 0x08082b2b082b082b, 0x08082b2b082b2b08, 0x08082b2b082b2b2b,
-    0x08082b2b19190808, 0x08082b2b2b192b19, 0x0819080808080819, 0x0819080808081908,
-    0x081908080808192b, 0x0819080808082b19, 0x0819080808190808, 0x081908080819082b,
-    0x0819080808191919, 0x0819080808192b08, 0x08190808082b0819, 0x08190808082b1908,
-    0x08190808082b192b, 0x0819080819080808, 0x081908081908082b, 0x0819080819081919,
-    0x0819080819082b08, 0x0819080819190819, 0x0819080819191908, 0x081908081919192b,
-    0x0819080819192b19, 0x08190808192b0808, 0x08190808192b082b, 0x08190808192b1919,
-    0x08190808192b2b08, 0x081908082b080819, 0x081908082b081908, 0x081908082b08192b,
-    0x081908082b190808, 0x081908082b191919, 0x081908082b192b08, 0x081908082b2b0819,
-    0x081908082b2b1908, 0x0819081908080808, 0x081908190808082b, 0x0819081908081919,
-    0x0819081908082b08, 0x0819081908082b2b, 0x0819081908190819, 0x0819081908191908,
-    0x081908190819192b, 0x0819081908192b19, 0x08190819082b0808, 0x08190819082b082b,
-    0x08190819082b1919, 0x08190819082b2b08, 0x0819081919080819, 0x0819081919081908,
-    0x081908191908192b, 0x0819081919082b19, 0x0819081919190808, 0x081908191919082b,
-    0x0819081919191919, 0x0819081919192b08, 0x08190819192b0819, 0x08190819192b1908,
-    0x081908192b080808, 0x081908192b08082b, 0x081908192b081919, 0x081908192b082b08,
-    0x081908192b190819, 0x081908192b191908, 0x0819082b08080819, 0x0819082b08081908,
-    0x0819082b08082b19, 0x0819082b08190808, 0x0819082b08191919, 0x0819082b082b0819,
-    0x0819082b082b1908, 0x0819082b19080808, 0x0819082b19081919, 0x0819082b19190819,
-    0x0819082b19191908, 0x0819082b2b080819, 0x0819082b2b081908, 0x0819082b2b190808,
-    0x0819190808080808, 0x081919080808082b, 0x0819190808081919, 0x0819190808082b08,
-    0x0819190808190819, 0x0819190808191908, 0x081919080819192b, 0x0819190808192b19,
-    0x08191908082b0808, 0x08191908082b1919, 0x08191908082b2b08, 0x0819190819080819,
-    0x0819190819081908, 0x081919081908192b, 0x0819190819082b19, 0x0819190819190808,
-    0x081919081919082b, 0x0819190819191919, 0x0819190819192b08, 0x08191908192b0819,
-    0x08191908192b1908, 0x081919082b080808, 0x081919082b08082b, 0x081919082b081919,
-    0x081919082b082b08, 0x081919082b190819, 0x081919082b191908, 0x081919082b2b0808,
-    0x0819191908080819, 0x0819191908081908, 0x081919190808192b, 0x0819191908082b19,
-    0x0819191908190808, 0x081919190819082b, 0x0819191908191919, 0x0819191908192b08,
-    0x08191919082b0819, 0x08191919082b1908, 0x0819191919080808, 0x081919191908082b,
-    0x0819191919081919, 0x0819191919082b08, 0x0819191919190819, 0x0819191919191908,
-    0x08191919192b0808, 0x081919192b080819, 0x081919192b081908, 0x081919192b190808,
-    0x0819192b08080808, 0x0819192b08081919, 0x0819192b08082b08, 0x0819192b08190819,
-    0x0819192b08191908, 0x0819192b082b0808, 0x0819192b19080819, 0x0819192b19081908,
-    0x0819192b19190808, 0x0819192b2b080808, 0x0819192b2b2b2b2b, 0x08192b0808080819,
-    0x08192b0808081908, 0x08192b080808192b, 0x08192b0808082b19, 0x08192b0808190808,
-    0x08192b0808191919, 0x08192b0808192b08, 0x08192b08082b0819, 0x08192b0819080808,
-    0x08192b081908082b, 0x08192b0819081919, 0x08192b0819082b08, 0x08192b0819190819,
-    0x08192b0819191908, 0x08192b08192b0808, 0x08192b082b080819, 0x08192b082b081908,
-    0x08192b1908080808, 0x08192b190808082b, 0x08192b1908081919, 0x08192b1908082b08,
-    0x08192b1908190819, 0x08192b1908191908, 0x08192b19082b0808, 0x08192b1919080819,
-    0x08192b1919081908, 0x08192b1919190808, 0x08192b19192b2b19, 0x08192b192b2b082b,
-    0x08192b2b08081908, 0x08192b2b08190808, 0x08192b2b19080808, 0x08192b2b1919192b,
-    0x082b080808080808, 0x082b08080808082b, 0x082b080808081919, 0x082b080808082b08,
-    0x082b080808190819, 0x082b080808191908, 0x082b08080819192b, 0x082b080808192b19,
-    0x082b0808082b0808, 0x082b0808082b1919, 0x082b0808082b2b2b, 0x082b080819080819,
-    0x082b080819081908, 0x082b080819190808, 0x082b08081919082b, 0x082b080819191919,
-    0x082b0808192b1908, 0x082b08082b080808, 0x082b08082b082b2b, 0x082b08082b191908,
-    0x082b08082b2b2b2b, 0x082b081908080819, 0x082b081908081908, 0x082b081908190808,
-    0x082b08190819082b, 0x082b081908191919, 0x082b0819082b0819, 0x082b081919080808,
-    0x082b08191908082b, 0x082b081919081919, 0x082b081919190819, 0x082b081919191908,
-    0x082b0819192b0808, 0x082b08192b080819, 0x082b08192b081908, 0x082b08192b190808,
-    0x082b082b08080808, 0x082b082b08082b2b, 0x082b082b082b082b, 0x082b082b082b2b08,
-    0x082b082b082b2b2b, 0x082b082b19081908, 0x082b082b19190808, 0x082b082b2b082b08,
-    0x082b082b2b082b2b, 0x082b082b2b2b2b08, 0x082b190808080819, 0x082b190808081908,
-    0x082b19080808192b, 0x082b190808082b19, 0x082b190808190808, 0x082b190808191919,
-    0x082b190808192b08, 0x082b1908082b0819, 0x082b1908082b1908, 0x082b190819080808,
-    0x082b19081908082b, 0x082b190819081919, 0x082b190819082b08, 0x082b190819190819,
-    0x082b190819191908, 0x082b1908192b0808, 0x082b19082b080819, 0x082b19082b081908,
-    0x082b19082b190808, 0x082b191908080808, 0x082b191908081919, 0x082b191908082b08,
-    0x082b191908190819, 0x082b191908191908, 0x082b1919082b0808, 0x082b191919080819,
-    0x082b191919081908, 0x082b191919190808, 0x082b1919192b192b, 0x082b19192b080808,
-    0x082b192b08080819, 0x082b192b08081908, 0x082b192b08190808, 0x082b192b19080808,
-    0x082b192b19192b19, 0x082b2b0808080808, 0x082b2b0808081919, 0x082b2b0808190819,
-    0x082b2b0808191908, 0x082b2b0819080819, 0x082b2b0819081908, 0x082b2b0819190808,
-    0x082b2b082b082b2b, 0x082b2b082b2b2b2b, 0x082b2b1908080819, 0x082b2b1908081908,
-    0x082b2b1908190808, 0x082b2b192b191919, 0x082b2b2b08082b2b, 0x082b2b2b082b082b,
-    0x082b2b2b192b1908, 0x082b2b2b2b082b08, 0x082b2b2b2b082b2b, 0x1908080808080819,
-    0x1908080808081908, 0x190808080808192b, 0x1908080808082b19, 0x1908080808190808,
-    0x190808080819082b, 0x1908080808191919, 0x1908080808192b08, 0x1908080808192b2b,
-    0x19080808082b0819, 0x19080808082b1908, 0x19080808082b192b, 0x1908080819080808,
-    0x190808081908082b, 0x1908080819081919, 0x1908080819082b08, 0x1908080819082b2b,
-    0x1908080819190819, 0x1908080819191908, 0x190808081919192b, 0x1908080819192b19,
-    0x19080808192b0808, 0x19080808192b082b, 0x19080808192b1919, 0x190808082b080819,
-    0x190808082b081908, 0x190808082b190808, 0x190808082b191919, 0x190808082b192b08,
-    0x190808082b2b0819, 0x190808082b2b1908, 0x1908081908080808, 0x190808190808082b,
-    0x1908081908081919, 0x1908081908082b08, 0x1908081908190819, 0x1908081908191908,
-    0x190808190819192b, 0x1908081908192b19, 0x19080819082b0808, 0x19080819082b082b,
-    0x19080819082b1919, 0x1908081919080819, 0x1908081919081908, 0x190808191908192b,
-    0x1908081919082b19, 0x1908081919190808, 0x190808191919082b, 0x1908081919191919,
-    0x1908081919192b08, 0x19080819192b0819, 0x19080819192b1908, 0x190808192b080808,
-    0x190808192b08082b, 0x190808192b081919, 0x190808192b082b08, 0x190808192b190819,
-    0x190808192b191908, 0x190808192b2b0808, 0x1908082b08080819, 0x1908082b08081908,
-    0x1908082b08190808, 0x1908082b0819082b, 0x1908082b08191919, 0x1908082b08192b08,
-    0x1908082b082b1908, 0x1908082b19080808, 0x1908082b19081919, 0x1908082b19082b08,
-    0x1908082b19190819, 0x1908082b19191908, 0x1908082b192b0808, 0x1908082b2b080819,
-    0x1908082b2b081908, 0x1908190808080808, 0x190819080808082b, 0x1908190808081919,
-    0x1908190808082b08, 0x1908190808082b2b, 0x1908190808190819, 0x1908190808191908,
-    0x190819080819192b, 0x1908190808192b19, 0x19081908082b0808, 0x19081908082b082b,
-    0x19081908082b1919, 0x19081908082b2b08, 0x1908190819080819, 0x1908190819081908,
-    0x190819081908192b, 0x1908190819082b19, 0x1908190819190808, 0x190819081919082b,
-    0x1908190819191919, 0x1908190819192b08, 0x19081908192b0819, 0x19081908192b1908,
-    0x190819082b080808, 0x190819082b08082b, 0x190819082b081919, 0x190819082b082b08,
-    0x190819082b190819, 0x190819082b191908, 0x190819082b2b0808, 0x1908191908080819,
-    0x1908191908081908, 0x190819190808192b, 0x1908191908082b19, 0x1908191908190808,
-    0x190819190819082b, 0x1908191908191919, 0x1908191908192b08, 0x19081919082b0819,
-    0x19081919082b1908, 0x1908191919080808, 0x190819191908082b, 0x1908191919081919,
-    0x1908191919082b08, 0x1908191919190819, 0x1908191919191908, 0x19081919192b0808,
-    0x19081919192b2b2b, 0x190819192b080819, 0x190819192b081908, 0x190819192b190808,
-    0x1908192b08080808, 0x1908192b0808082b, 0x1908192b08081919, 0x1908192b08082b08,
-    0x1908192b08190819, 0x1908192b08191908, 0x1908192b082b0808, 0x1908192b19080819,
-    0x1908192b19081908, 0x1908192b19190808, 0x1908192b2b080808, 0x1908192b2b2b1919,
-    0x19082b0808080819, 0x19082b0808081908, 0x19082b0808082b19, 0x19082b0808190808,
-    0x19082b080819082b, 0x19082b0808191919, 0x19082b0808192b08, 0x19082b08082b0819,
-    0x19082b08082b1908, 0x19082b0819080808, 0x19082b081908082b, 0x19082b0819081919,
-    0x19082b0819082b08, 0x19082b0819190819, 0x19082b0819191908, 0x19082b08192b0808,
-    0x19082b082b081908, 0x19082b082b190808, 0x19082b1908080808, 0x19082b190808082b,
-    0x19082b1908081919, 0x19082b1908082b08, 0x19082b1908190819, 0x19082b1908191908,
-    0x19082b19082b0808, 0x19082b1919080819, 0x19082b1919081908, 0x19082b1919190808,
-    0x19082b192b080808, 0x19082b192b19192b, 0x19082b2b08080819, 0x19082b2b08081908,
-    0x19082b2b08190808, 0x19082b2b19080808, 0x1919080808080808, 0x191908080808082b,
-    0x1919080808081919, 0x1919080808082b08, 0x1919080808190819, 0x1919080808191908,
-    0x191908080819192b, 0x1919080808192b19, 0x19190808082b0808, 0x19190808082b082b,
-    0x19190808082b1919, 0x19190808082b2b08, 0x1919080819080819, 0x1919080819081908,
-    0x191908081908192b, 0x1919080819082b19, 0x1919080819190808, 0x191908081919082b,
-    0x1919080819191919, 0x1919080819192b08, 0x19190808192b0819, 0x19190808192b1908,
-    0x191908082b080808, 0x191908082b08082b, 0x191908082b081919, 0x191908082b082b08,
-    0x191908082b190819, 0x191908082b191908, 0x1919081908080819, 0x1919081908081908,
-    0x191908190808192b, 0x1919081908082b19, 0x1919081908190808, 0x191908190819082b,
-    0x1919081908191919, 0x1919081908192b08, 0x19190819082b0819, 0x19190819082b1908,
-    0x1919081919080808, 0x191908191908082b, 0x1919081919081919, 0x1919081919082b08,
-    0x1919081919190819, 0x1919081919191908, 0x19190819192b0808, 0x191908192b080819,
-    0x191908192b081908, 0x191908192b190808, 0x1919082b08080808, 0x1919082b08081919,
-    0x1919082b08082b08, 0x1919082b08190819, 0x1919082b08191908, 0x1919082b082b0808,
-    0x1919082b19080819, 0x1919082b19081908, 0x1919082b19190808, 0x1919082b192b2b19,
-    0x1919082b2b080808, 0x1919190808080819, 0x1919190808081908, 0x191919080808192b,
-    0x1919190808082b19, 0x1919190808190808, 0x191919080819082b, 0x1919190808191919,
-    0x1919190808192b08, 0x19191908082b0819, 0x19191908082b1908, 0x1919190819080808,
-    0x191919081908082b, 0x1919190819081919, 0x1919190819082b08, 0x1919190819190819,
-    0x1919190819191908, 0x19191908192b0808, 0x191919082b080819, 0x191919082b081908,
-    0x191919082b190808, 0x1919191908080808, 0x191919190808082b, 0x1919191908081919,
-    0x1919191908082b08, 0x1919191908190819, 0x1919191908191908, 0x19191919082b0808,
-    0x1919191919080819, 0x1919191919081908, 0x1919191919190808, 0x191919192b080808,
-    0x1919192b08080819, 0x1919192b08081908, 0x1919192b08190808, 0x1919192b082b192b,
-    0x1919192b19080808, 0x19192b0808080808, 0x19192b080808082b, 0x19192b0808081919,
-    0x19192b0808082b08, 0x19192b0808190819, 0x19192b0808191908, 0x19192b08082b0808,
-    0x19192b0819080819, 0x19192b0819081908, 0x19192b0819190808, 0x19192b0819192b2b,
-    0x19192b082b080808, 0x19192b1908080819, 0x19192b1908081908, 0x19192b1908190808,
-    0x19192b1919080808, 0x19192b2b08080808, 0x19192b2b08192b19, 0x19192b2b2b081919,
-    0x19192b2b2b2b2b08, 0x192b080808080819, 0x192b080808081908, 0x192b08080808192b,
-    0x192b080808190808, 0x192b08080819082b, 0x192b080808191919, 0x192b080808192b08,
-    0x192b0808082b0819, 0x192b0808082b1908, 0x192b080819080808, 0x192b080819081919,
-    0x192b080819082b08, 0x192b080819190819, 0x192b080819191908, 0x192b0808192b0808,
-    0x192b08082b081908, 0x192b08082b190808, 0x192b081908080808, 0x192b08190808082b,
-    0x192b081908081919, 0x192b081908082b08, 0x192b081908190819, 0x192b081908191908,
-    0x192b0819082b0808, 0x192b081919080819, 0x192b081919081908, 0x192b081919190808,
-    0x192b08192b080808, 0x192b08192b192b19, 0x192b082b08081908, 0x192b082b08190808,
-    0x192b082b19080808, 0x192b082b1919192b, 0x192b082b2b2b0819, 0x192b190808080808,
-    0x192b190808081919, 0x192b190808082b08, 0x192b190808190819, 0x192b190808191908,
-    0x192b1908082b0808, 0x192b190819080819, 0x192b190819081908, 0x192b190819190808,
-    0x192b19082b080808, 0x192b191908080819, 0x192b191908081908, 0x192b191908190808,
-    0x192b191919080808, 0x192b191919082b2b, 0x192b1919192b2b08, 0x192b19192b19082b,
-    0x192b192b08080808, 0x192b192b2b191908, 0x192b2b0808080819, 0x192b2b0808081908,
-    0x192b2b0808190808, 0x192b2b08192b1919, 0x192b2b082b192b08, 0x192b2b1908080808,
-    0x192b2b19082b2b2b, 0x192b2b2b1908082b, 0x192b2b2b2b2b0819, 0x2b08080808080808,
-    0x2b0808080808082b, 0x2b08080808081919, 0x2b08080808082b08, 0x2b08080808190819,
-    0x2b08080808191908, 0x2b08080808192b19, 0x2b080808082b0808, 0x2b080808082b1919,
-    0x2b08080819080819, 0x2b08080819081908, 0x2b08080819190808, 0x2b0808081919082b,
-    0x2b08080819191919, 0x2b08080819192b08, 0x2b080808192b0819, 0x2b0808082b080808,
-    0x2b0808082b081919, 0x2b0808082b190819, 0x2b0808082b191908, 0x2b08081908080819,
-    0x2b08081908081908, 0x2b08081908082b19, 0x2b08081908190808, 0x2b0808190819082b,
-    0x2b08081908191919, 0x2b08081908192b08, 0x2b080819082b0819, 0x2b080819082b1908,
-    0x2b08081919080808, 0x2b0808191908082b, 0x2b08081919081919, 0x2b08081919082b08,
-    0x2b08081919190819, 0x2b08081919191908, 0x2b0808192b080819, 0x2b0808192b081908,
-    0x2b0808192b190808, 0x2b0808192b2b2b19, 0x2b08082b08080808, 0x2b08082b08081919,
-    0x2b08082b08082b2b, 0x2b08082b08190819, 0x2b08082b08191908, 0x2b08082b19080819,
-    0x2b08082b19081908, 0x2b08082b19190808, 0x2b08190808080819, 0x2b08190808081908,
-    0x2b0819080808192b, 0x2b08190808082b19, 0x2b08190808190808, 0x2b0819080819082b,
-    0x2b08190808191919, 0x2b08190808192b08, 0x2b081908082b0819, 0x2b08190819080808,
-    0x2b0819081908082b, 0x2b08190819081919, 0x2b08190819082b08, 0x2b08190819190819,
-    0x2b08190819191908, 0x2b081908192b0808, 0x2b0819082b080819, 0x2b0819082b081908,
-    0x2b0819082b190808, 0x2b08191908080808, 0x2b0819190808082b, 0x2b08191908081919,
-    0x2b08191908082b08, 0x2b08191908190819, 0x2b08191908191908, 0x2b081919082b0808,
-    0x2b08191919080819, 0x2b08191919081908, 0x2b08191919190808, 0x2b0819192b080808,
-    0x2b0819192b082b2b, 0x2b08192b08080819, 0x2b08192b08081908, 0x2b08192b08190808,
-    0x2b08192b082b2b19, 0x2b08192b19080808, 0x2b082b0808080808, 0x2b082b0808081919,
-    0x2b082b0808190819, 0x2b082b0808191908, 0x2b082b0819080819, 0x2b082b0819081908,
-    0x2b082b0819190808, 0x2b082b082b2b082b, 0x2b082b1908080819, 0x2b082b1908081908,
-    0x2b082b1919080808, 0x2b082b19192b1919, 0x2b082b2b082b082b, 0x2b082b2b19192b08,
-    0x2b082b2b19192b2b, 0x2b082b2b2b08082b, 0x2b082b2b2b2b082b, 0x2b19080808080819,
-    0x2b19080808081908, 0x2b19080808082b19, 0x2b19080808190808, 0x2b1908080819082b,
-    0x2b19080808191919, 0x2b19080808192b08, 0x2b190808082b1908, 0x2b19080819080808,
-    0x2b1908081908082b, 0x2b19080819081919, 0x2b19080819082b08, 0x2b19080819190819,
-    0x2b19080819191908, 0x2b190808192b0808, 0x2b1908082b080819, 0x2b1908082b081908,
-    0x2b1908082b190808, 0x2b19081908080808, 0x2b19081908081919, 0x2b19081908190819,
-    0x2b19081908191908, 0x2b19081919080819, 0x2b19081919081908, 0x2b19081919190808,
-    0x2b19081919192b2b, 0x2b19082b08080819, 0x2b19082b08081908, 0x2b19082b08190808,
-    0x2b19082b19080808, 0x2b19082b2b2b192b, 0x2b19190808080808, 0x2b1919080808082b,
-    0x2b19190808081919, 0x2b19190808082b08, 0x2b19190808190819, 0x2b19190808191908,
-    0x2b191908082b0808, 0x2b19190819080819, 0x2b19190819081908, 0x2b19190819190808,
-    0x2b1919082b080808, 0x2b1919082b19192b, 0x2b19191908080819, 0x2b19191908081908,
-    0x2b19191908190808, 0x2b19191919080808, 0x2b1919192b192b08, 0x2b1919192b2b0819,
-    0x2b19192b08080808, 0x2b19192b1908192b, 0x2b19192b192b1908, 0x2b192b0808080819,
-    0x2b192b0808081908, 0x2b192b0808190808, 0x2b192b08082b192b, 0x2b192b0819080808,
-    0x2b192b082b2b2b19, 0x2b192b1908080808, 0x2b192b1919082b19, 0x2b192b191919082b,
-    0x2b192b2b2b190808, 0x2b2b080808080808, 0x2b2b080808081919, 0x2b2b080808082b2b,
-    0x2b2b080808191908, 0x2b2b0808082b082b, 0x2b2b0808082b2b2b, 0x2b2b080819080819,
-    0x2b2b080819081908, 0x2b2b080819190808, 0x2b2b08082b2b082b, 0x2b2b08082b2b2b2b,
-    0x2b2b081919080808, 0x2b2b0819192b1919, 0x2b2b082b0808082b, 0x2b2b082b08082b2b,
-    0x2b2b082b082b082b, 0x2b2b082b082b2b08, 0x2b2b082b082b2b2b, 0x2b2b082b2b08082b,
-    0x2b2b082b2b082b08, 0x2b2b082b2b082b2b, 0x2b2b082b2b2b2b08, 0x2b2b190808080819,
-    0x2b2b190808081908, 0x2b2b190808190808, 0x2b2b190819080808, 0x2b2b19082b082b19,
-    0x2b2b19082b2b1908, 0x2b2b191908080808, 0x2b2b191908192b19, 0x2b2b192b19190819,
-    0x2b2b2b0808082b2b, 0x2b2b2b08082b2b08, 0x2b2b2b082b2b082b, 0x2b2b2b1919191908,
-    0x2b2b2b192b08192b, 0x2b2b2b2b08082b08, 0x2b2b2b2b08082b2b, 0x2b2b2b2b082b0808,
-    0x2b2b2b2b082b082b, 0x2b2b2b2b082b2b08, 0x2b2b2b2b2b082b08, 0x2b2b2b2b2b2b2b2b,
-};
-
-static const uint32_t iq3xxs_grid[256] = {
-    0x04040404, 0x04040414, 0x04040424, 0x04040c0c, 0x04040c1c, 0x04040c3e, 0x04041404, 0x04041414,
-    0x04041c0c, 0x04042414, 0x04043e1c, 0x04043e2c, 0x040c040c, 0x040c041c, 0x040c0c04, 0x040c0c14,
-    0x040c140c, 0x040c142c, 0x040c1c04, 0x040c1c14, 0x040c240c, 0x040c2c24, 0x040c3e04, 0x04140404,
-    0x04140414, 0x04140424, 0x04140c0c, 0x04141404, 0x04141414, 0x04141c0c, 0x04141c1c, 0x04141c3e,
-    0x04142c0c, 0x04142c3e, 0x04143e2c, 0x041c040c, 0x041c043e, 0x041c0c04, 0x041c0c14, 0x041c142c,
-    0x041c3e04, 0x04240c1c, 0x04241c3e, 0x04242424, 0x04242c3e, 0x04243e1c, 0x04243e2c, 0x042c040c,
-    0x042c043e, 0x042c1c14, 0x042c2c14, 0x04341c2c, 0x04343424, 0x043e0c04, 0x043e0c24, 0x043e0c34,
-    0x043e241c, 0x043e340c, 0x0c04040c, 0x0c04041c, 0x0c040c04, 0x0c040c14, 0x0c04140c, 0x0c04141c,
-    0x0c041c04, 0x0c041c14, 0x0c041c24, 0x0c04243e, 0x0c042c04, 0x0c0c0404, 0x0c0c0414, 0x0c0c0c0c,
-    0x0c0c1404, 0x0c0c1414, 0x0c14040c, 0x0c14041c, 0x0c140c04, 0x0c140c14, 0x0c14140c, 0x0c141c04,
-    0x0c143e14, 0x0c1c0404, 0x0c1c0414, 0x0c1c1404, 0x0c1c1c0c, 0x0c1c2434, 0x0c1c3434, 0x0c24040c,
-    0x0c24042c, 0x0c242c04, 0x0c2c1404, 0x0c2c1424, 0x0c2c2434, 0x0c2c3e0c, 0x0c34042c, 0x0c3e1414,
-    0x0c3e2404, 0x14040404, 0x14040414, 0x14040c0c, 0x14040c1c, 0x14041404, 0x14041414, 0x14041434,
-    0x14041c0c, 0x14042414, 0x140c040c, 0x140c041c, 0x140c042c, 0x140c0c04, 0x140c0c14, 0x140c140c,
-    0x140c1c04, 0x140c341c, 0x140c343e, 0x140c3e04, 0x14140404, 0x14140414, 0x14140c0c, 0x14140c3e,
-    0x14141404, 0x14141414, 0x14141c3e, 0x14142404, 0x14142c2c, 0x141c040c, 0x141c0c04, 0x141c0c24,
-    0x141c3e04, 0x141c3e24, 0x14241c2c, 0x14242c1c, 0x142c041c, 0x142c143e, 0x142c240c, 0x142c3e24,
-    0x143e040c, 0x143e041c, 0x143e0c34, 0x143e242c, 0x1c04040c, 0x1c040c04, 0x1c040c14, 0x1c04140c,
-    0x1c04141c, 0x1c042c04, 0x1c04342c, 0x1c043e14, 0x1c0c0404, 0x1c0c0414, 0x1c0c1404, 0x1c0c1c0c,
-    0x1c0c2424, 0x1c0c2434, 0x1c14040c, 0x1c14041c, 0x1c140c04, 0x1c14142c, 0x1c142c14, 0x1c143e14,
-    0x1c1c0c0c, 0x1c1c1c1c, 0x1c241c04, 0x1c24243e, 0x1c243e14, 0x1c2c0404, 0x1c2c0434, 0x1c2c1414,
-    0x1c2c2c2c, 0x1c340c24, 0x1c341c34, 0x1c34341c, 0x1c3e1c1c, 0x1c3e3404, 0x24040424, 0x24040c3e,
-    0x24041c2c, 0x24041c3e, 0x24042c1c, 0x24042c3e, 0x240c3e24, 0x24141404, 0x24141c3e, 0x24142404,
-    0x24143404, 0x24143434, 0x241c043e, 0x241c242c, 0x24240424, 0x24242c0c, 0x24243424, 0x242c142c,
-    0x242c241c, 0x242c3e04, 0x243e042c, 0x243e0c04, 0x243e0c14, 0x243e1c04, 0x2c040c14, 0x2c04240c,
-    0x2c043e04, 0x2c0c0404, 0x2c0c0434, 0x2c0c1434, 0x2c0c2c2c, 0x2c140c24, 0x2c141c14, 0x2c143e14,
-    0x2c1c0414, 0x2c1c2c1c, 0x2c240c04, 0x2c24141c, 0x2c24143e, 0x2c243e14, 0x2c2c0414, 0x2c2c1c0c,
-    0x2c342c04, 0x2c3e1424, 0x2c3e2414, 0x34041424, 0x34042424, 0x34042434, 0x34043424, 0x340c140c,
-    0x340c340c, 0x34140c3e, 0x34143424, 0x341c1c04, 0x341c1c34, 0x34242424, 0x342c042c, 0x342c2c14,
-    0x34341c1c, 0x343e041c, 0x343e140c, 0x3e04041c, 0x3e04042c, 0x3e04043e, 0x3e040c04, 0x3e041c14,
-    0x3e042c14, 0x3e0c1434, 0x3e0c2404, 0x3e140c14, 0x3e14242c, 0x3e142c14, 0x3e1c0404, 0x3e1c0c2c,
-    0x3e1c1c1c, 0x3e1c3404, 0x3e24140c, 0x3e24240c, 0x3e2c0404, 0x3e2c0414, 0x3e2c1424, 0x3e341c04,
-};
-
-static const uint32_t iq3s_grid[512] = {
-    0x01010101, 0x01010103, 0x01010105, 0x0101010b, 0x0101010f, 0x01010301, 0x01010303, 0x01010305,
-    0x01010309, 0x0101030d, 0x01010501, 0x01010503, 0x0101050b, 0x01010707, 0x01010901, 0x01010905,
-    0x0101090b, 0x0101090f, 0x01010b03, 0x01010b07, 0x01010d01, 0x01010d05, 0x01010f03, 0x01010f09,
-    0x01010f0f, 0x01030101, 0x01030103, 0x01030105, 0x01030109, 0x01030301, 0x01030303, 0x0103030b,
-    0x01030501, 0x01030507, 0x0103050f, 0x01030703, 0x0103070b, 0x01030909, 0x01030d03, 0x01030d0b,
-    0x01030f05, 0x01050101, 0x01050103, 0x0105010b, 0x0105010f, 0x01050301, 0x01050307, 0x0105030d,
-    0x01050503, 0x0105050b, 0x01050701, 0x01050709, 0x01050905, 0x0105090b, 0x0105090f, 0x01050b03,
-    0x01050b07, 0x01050f01, 0x01050f07, 0x01070107, 0x01070303, 0x0107030b, 0x01070501, 0x01070505,
-    0x01070703, 0x01070707, 0x0107070d, 0x01070909, 0x01070b01, 0x01070b05, 0x01070d0f, 0x01070f03,
-    0x01070f0b, 0x01090101, 0x01090307, 0x0109030f, 0x01090503, 0x01090509, 0x01090705, 0x01090901,
-    0x01090907, 0x01090b03, 0x01090f01, 0x010b0105, 0x010b0109, 0x010b0501, 0x010b0505, 0x010b050d,
-    0x010b0707, 0x010b0903, 0x010b090b, 0x010b090f, 0x010b0d0d, 0x010b0f07, 0x010d010d, 0x010d0303,
-    0x010d0307, 0x010d0703, 0x010d0b05, 0x010d0f03, 0x010f0101, 0x010f0105, 0x010f0109, 0x010f0501,
-    0x010f0505, 0x010f050d, 0x010f0707, 0x010f0b01, 0x010f0b09, 0x03010101, 0x03010103, 0x03010105,
-    0x03010109, 0x03010301, 0x03010303, 0x03010307, 0x0301030b, 0x0301030f, 0x03010501, 0x03010505,
-    0x03010703, 0x03010709, 0x0301070d, 0x03010b09, 0x03010b0d, 0x03010d03, 0x03010f05, 0x03030101,
-    0x03030103, 0x03030107, 0x0303010d, 0x03030301, 0x03030309, 0x03030503, 0x03030701, 0x03030707,
-    0x03030903, 0x03030b01, 0x03030b05, 0x03030f01, 0x03030f0d, 0x03050101, 0x03050305, 0x0305030b,
-    0x0305030f, 0x03050501, 0x03050509, 0x03050705, 0x03050901, 0x03050907, 0x03050b0b, 0x03050d01,
-    0x03050f05, 0x03070103, 0x03070109, 0x0307010f, 0x03070301, 0x03070307, 0x03070503, 0x0307050f,
-    0x03070701, 0x03070709, 0x03070903, 0x03070d05, 0x03070f01, 0x03090107, 0x0309010b, 0x03090305,
-    0x03090309, 0x03090703, 0x03090707, 0x03090905, 0x0309090d, 0x03090b01, 0x03090b09, 0x030b0103,
-    0x030b0301, 0x030b0307, 0x030b0503, 0x030b0701, 0x030b0705, 0x030b0b03, 0x030d0501, 0x030d0509,
-    0x030d050f, 0x030d0909, 0x030d090d, 0x030f0103, 0x030f0107, 0x030f0301, 0x030f0305, 0x030f0503,
-    0x030f070b, 0x030f0903, 0x030f0d05, 0x030f0f01, 0x05010101, 0x05010103, 0x05010107, 0x0501010b,
-    0x0501010f, 0x05010301, 0x05010305, 0x05010309, 0x0501030d, 0x05010503, 0x05010507, 0x0501050f,
-    0x05010701, 0x05010705, 0x05010903, 0x05010907, 0x0501090b, 0x05010b01, 0x05010b05, 0x05010d0f,
-    0x05010f01, 0x05010f07, 0x05010f0b, 0x05030101, 0x05030105, 0x05030301, 0x05030307, 0x0503030f,
-    0x05030505, 0x0503050b, 0x05030703, 0x05030709, 0x05030905, 0x05030b03, 0x05050103, 0x05050109,
-    0x0505010f, 0x05050503, 0x05050507, 0x05050701, 0x0505070f, 0x05050903, 0x05050b07, 0x05050b0f,
-    0x05050f03, 0x05050f09, 0x05070101, 0x05070105, 0x0507010b, 0x05070303, 0x05070505, 0x05070509,
-    0x05070703, 0x05070707, 0x05070905, 0x05070b01, 0x05070d0d, 0x05090103, 0x0509010f, 0x05090501,
-    0x05090507, 0x05090705, 0x0509070b, 0x05090903, 0x05090f05, 0x05090f0b, 0x050b0109, 0x050b0303,
-    0x050b0505, 0x050b070f, 0x050b0901, 0x050b0b07, 0x050b0f01, 0x050d0101, 0x050d0105, 0x050d010f,
-    0x050d0503, 0x050d0b0b, 0x050d0d03, 0x050f010b, 0x050f0303, 0x050f050d, 0x050f0701, 0x050f0907,
-    0x050f0b01, 0x07010105, 0x07010303, 0x07010307, 0x0701030b, 0x0701030f, 0x07010505, 0x07010703,
-    0x07010707, 0x0701070b, 0x07010905, 0x07010909, 0x0701090f, 0x07010b03, 0x07010d07, 0x07010f03,
-    0x07030103, 0x07030107, 0x0703010b, 0x07030309, 0x07030503, 0x07030507, 0x07030901, 0x07030d01,
-    0x07030f05, 0x07030f0d, 0x07050101, 0x07050305, 0x07050501, 0x07050705, 0x07050709, 0x07050b01,
-    0x07070103, 0x07070301, 0x07070309, 0x07070503, 0x07070507, 0x0707050f, 0x07070701, 0x07070903,
-    0x07070907, 0x0707090f, 0x07070b0b, 0x07070f07, 0x07090107, 0x07090303, 0x0709030d, 0x07090505,
-    0x07090703, 0x07090b05, 0x07090d01, 0x07090d09, 0x070b0103, 0x070b0301, 0x070b0305, 0x070b050b,
-    0x070b0705, 0x070b0909, 0x070b0b0d, 0x070b0f07, 0x070d030d, 0x070d0903, 0x070f0103, 0x070f0107,
-    0x070f0501, 0x070f0505, 0x070f070b, 0x09010101, 0x09010109, 0x09010305, 0x09010501, 0x09010509,
-    0x0901050f, 0x09010705, 0x09010903, 0x09010b01, 0x09010f01, 0x09030105, 0x0903010f, 0x09030303,
-    0x09030307, 0x09030505, 0x09030701, 0x0903070b, 0x09030907, 0x09030b03, 0x09030b0b, 0x09050103,
-    0x09050107, 0x09050301, 0x0905030b, 0x09050503, 0x09050707, 0x09050901, 0x09050b0f, 0x09050d05,
-    0x09050f01, 0x09070109, 0x09070303, 0x09070307, 0x09070501, 0x09070505, 0x09070703, 0x0907070b,
-    0x09090101, 0x09090105, 0x09090509, 0x0909070f, 0x09090901, 0x09090f03, 0x090b010b, 0x090b010f,
-    0x090b0503, 0x090b0d05, 0x090d0307, 0x090d0709, 0x090d0d01, 0x090f0301, 0x090f030b, 0x090f0701,
-    0x090f0907, 0x090f0b03, 0x0b010105, 0x0b010301, 0x0b010309, 0x0b010505, 0x0b010901, 0x0b010909,
-    0x0b01090f, 0x0b010b05, 0x0b010d0d, 0x0b010f09, 0x0b030103, 0x0b030107, 0x0b03010b, 0x0b030305,
-    0x0b030503, 0x0b030705, 0x0b030f05, 0x0b050101, 0x0b050303, 0x0b050507, 0x0b050701, 0x0b05070d,
-    0x0b050b07, 0x0b070105, 0x0b07010f, 0x0b070301, 0x0b07050f, 0x0b070909, 0x0b070b03, 0x0b070d0b,
-    0x0b070f07, 0x0b090103, 0x0b090109, 0x0b090501, 0x0b090705, 0x0b09090d, 0x0b0b0305, 0x0b0b050d,
-    0x0b0b0b03, 0x0b0b0b07, 0x0b0d0905, 0x0b0f0105, 0x0b0f0109, 0x0b0f0505, 0x0d010303, 0x0d010307,
-    0x0d01030b, 0x0d010703, 0x0d010707, 0x0d010d01, 0x0d030101, 0x0d030501, 0x0d03050f, 0x0d030d09,
-    0x0d050305, 0x0d050709, 0x0d050905, 0x0d050b0b, 0x0d050d05, 0x0d050f01, 0x0d070101, 0x0d070309,
-    0x0d070503, 0x0d070901, 0x0d09050b, 0x0d090907, 0x0d090d05, 0x0d0b0101, 0x0d0b0107, 0x0d0b0709,
-    0x0d0b0d01, 0x0d0d010b, 0x0d0d0901, 0x0d0f0303, 0x0d0f0307, 0x0f010101, 0x0f010109, 0x0f01010f,
-    0x0f010501, 0x0f010505, 0x0f01070d, 0x0f010901, 0x0f010b09, 0x0f010d05, 0x0f030105, 0x0f030303,
-    0x0f030509, 0x0f030907, 0x0f03090b, 0x0f050103, 0x0f050109, 0x0f050301, 0x0f05030d, 0x0f050503,
-    0x0f050701, 0x0f050b03, 0x0f070105, 0x0f070705, 0x0f07070b, 0x0f070b07, 0x0f090103, 0x0f09010b,
-    0x0f090307, 0x0f090501, 0x0f090b01, 0x0f0b0505, 0x0f0b0905, 0x0f0d0105, 0x0f0d0703, 0x0f0f0101,
-};
-
-#define NGRID_IQ2XXS 512
-static const  uint64_t iq1s_grid[NGRID_IQ2XXS] = {
-    0xffffffffffff0101, 0xffffffffff01ff00, 0xffffffffff010100, 0xffffffff00000000,
-    0xffffffff01ff00ff, 0xffffffff01ff0001, 0xffffffff0101ffff, 0xffffffff0101ff01,
-    0xffffff00ff000000, 0xffffff000000ff00, 0xffffff00000000ff, 0xffffff0000000100,
-    0xffffff0000010000, 0xffffff0001000000, 0xffffff01ffff00ff, 0xffffff01ff01ff00,
-    0xffffff01ff010100, 0xffffff0100000001, 0xffffff0101ffff00, 0xffffff0101ff0101,
-    0xffffff0101010100, 0xffff00ffff00ff01, 0xffff00ffff0000ff, 0xffff00ff00ff0100,
-    0xffff00ff0100ff00, 0xffff00ff010001ff, 0xffff0000ff0101ff, 0xffff000000ffff00,
-    0xffff000000000000, 0xffff00000001ff01, 0xffff000001000101, 0xffff0000010100ff,
-    0xffff0001ffff0100, 0xffff00010000ff00, 0xffff000100010101, 0xffff000101000000,
-    0xffff01ffffff0000, 0xffff01ffff01ffff, 0xffff01ffff010100, 0xffff01ff00000000,
-    0xffff01ff01ffffff, 0xffff01ff01ff0001, 0xffff01ff0101ffff, 0xffff01ff01010001,
-    0xffff0100ffffff01, 0xffff01000000ffff, 0xffff010000000100, 0xffff010001ff01ff,
-    0xffff010001000000, 0xffff0101ff000000, 0xffff0101000101ff, 0xffff010101ffff01,
-    0xffff01010101ff00, 0xff00ffffff000000, 0xff00ffff00ffff00, 0xff00ffff00000001,
-    0xff00ffff000001ff, 0xff00ffff01010000, 0xff00ff00ffff0000, 0xff00ff00ff00ff00,
-    0xff00ff00ff0000ff, 0xff00ff00ff000100, 0xff00ff00ff010001, 0xff00ff0000ff0001,
-    0xff00ff000000ffff, 0xff00ff0000000000, 0xff00ff000001ff00, 0xff00ff0000010100,
-    0xff00ff0001ff0000, 0xff00ff000100ff00, 0xff00ff0001000100, 0xff00ff01ff000000,
-    0xff00ff0100ff0000, 0xff00ff01000001ff, 0xff00ff0101010001, 0xff0000ff00000000,
-    0xff0000ff0001ff00, 0xff0000ff00010100, 0xff000000ffff0101, 0xff000000ff000000,
-    0xff000000ff01ff00, 0xff00000000ff0000, 0xff0000000000ff00, 0xff000000000000ff,
-    0xff00000000000000, 0xff00000000000001, 0xff00000000000100, 0xff0000000001ffff,
-    0xff00000000010000, 0xff00000001000000, 0xff00000001010100, 0xff000001ff00ff01,
-    0xff000001ff0100ff, 0xff00000100000000, 0xff0000010001ff00, 0xff00000101ff0100,
-    0xff0000010100ff00, 0xff0001ff00ff00ff, 0xff0001ff00000101, 0xff0001ff000100ff,
-    0xff0001ff01000000, 0xff000100ff0001ff, 0xff0001000000ff01, 0xff00010000000000,
-    0xff00010000010001, 0xff00010000010100, 0xff00010001ffff00, 0xff00010001ff0101,
-    0xff00010001010000, 0xff000101ffffffff, 0xff000101ff000101, 0xff00010101ff00ff,
-    0xff00010101000001, 0xff000101010100ff, 0xff01ffffff000101, 0xff01ffffff01ffff,
-    0xff01ffffff01ff01, 0xff01ffffff0101ff, 0xff01ffff00000000, 0xff01ffff01ff0001,
-    0xff01ffff0101ff01, 0xff01ff00ff000000, 0xff01ff0000ff0100, 0xff01ff000000ff01,
-    0xff01ff0000010000, 0xff01ff00010000ff, 0xff01ff01ff01ff00, 0xff01ff0100000101,
-    0xff0100ffffff0000, 0xff0100ffff010000, 0xff0100ff01ff00ff, 0xff0100ff01000100,
-    0xff0100ff010100ff, 0xff010000ffffff01, 0xff01000000000000, 0xff0100000101ff00,
-    0xff010001ffff00ff, 0xff010001ff000100, 0xff01000100ffff00, 0xff01000100010001,
-    0xff01000101ff0001, 0xff010001010001ff, 0xff0101ffffffffff, 0xff0101ffff01ffff,
-    0xff0101ffff010101, 0xff0101ff0000ff00, 0xff0101ff01010001, 0xff010100ff000000,
-    0xff010100ff01ff01, 0xff01010000ff0001, 0xff01010000000100, 0xff01010001000000,
-    0xff0101010100ffff, 0x00ffffff0000ff01, 0x00ffffff000000ff, 0x00ffffff00000100,
-    0x00ffffff00010000, 0x00ffff00ffff0001, 0x00ffff00ff0000ff, 0x00ffff00ff000100,
-    0x00ffff0000000000, 0x00ffff0001000100, 0x00ffff0001010001, 0x00ffff01ff00ff01,
-    0x00ffff0100ff0100, 0x00ffff010000ff00, 0x00ffff01000100ff, 0x00ffff0101ff00ff,
-    0x00ffff010101ff00, 0x00ff00ffffffffff, 0x00ff00ffffff01ff, 0x00ff00ffff000101,
-    0x00ff00ff00000000, 0x00ff00ff000101ff, 0x00ff00ff01010101, 0x00ff0000ff000000,
-    0x00ff0000ff01ffff, 0x00ff000000ff0000, 0x00ff00000000ff00, 0x00ff0000000000ff,
-    0x00ff000000000000, 0x00ff000000000001, 0x00ff000000000100, 0x00ff000000010000,
-    0x00ff000001ffff01, 0x00ff000001000000, 0x00ff0001ff000101, 0x00ff000100ffffff,
-    0x00ff000100000000, 0x00ff0001010001ff, 0x00ff01ffff000000, 0x00ff01ff0001ff00,
-    0x00ff01ff01ff0100, 0x00ff0100ff01ff01, 0x00ff010000ff00ff, 0x00ff010000ff0101,
-    0x00ff010000000000, 0x00ff010000010101, 0x00ff01000100ff00, 0x00ff010001010000,
-    0x00ff0101ffffff00, 0x00ff01010000ff01, 0x00ff010100000100, 0x00ff010101ff0000,
-    0x0000ffffffff0100, 0x0000ffffff00ff00, 0x0000ffffff0000ff, 0x0000ffffff010000,
-    0x0000ffff00000000, 0x0000ffff00010101, 0x0000ffff01ffff01, 0x0000ffff01000100,
-    0x0000ff00ff000000, 0x0000ff00ff01ff00, 0x0000ff00ff0101ff, 0x0000ff0000ff0000,
-    0x0000ff000000ff00, 0x0000ff00000000ff, 0x0000ff0000000000, 0x0000ff0000000001,
-    0x0000ff0000000100, 0x0000ff0000010000, 0x0000ff0001ffffff, 0x0000ff0001ff01ff,
-    0x0000ff0001000000, 0x0000ff000101ffff, 0x0000ff01ffff0101, 0x0000ff01ff010000,
-    0x0000ff0100000000, 0x0000ff0101000101, 0x000000ffffff0001, 0x000000ffff000000,
-    0x000000ff00ff0000, 0x000000ff0000ff00, 0x000000ff000000ff, 0x000000ff00000000,
-    0x000000ff00000001, 0x000000ff00000100, 0x000000ff00010000, 0x000000ff01000000,
-    0x000000ff0101ff00, 0x00000000ffff0000, 0x00000000ff00ff00, 0x00000000ff0000ff,
-    0x00000000ff000000, 0x00000000ff000001, 0x00000000ff000100, 0x00000000ff010000,
-    0x0000000000ffff00, 0x0000000000ff00ff, 0x0000000000ff0000, 0x0000000000ff0001,
-    0x0000000000ff0100, 0x000000000000ffff, 0x000000000000ff00, 0x000000000000ff01,
-    0x00000000000000ff, 0x0000000000000001, 0x00000000000001ff, 0x0000000000000100,
-    0x0000000000000101, 0x000000000001ff00, 0x00000000000100ff, 0x0000000000010000,
-    0x0000000000010001, 0x0000000000010100, 0x0000000001ff0000, 0x000000000100ff00,
-    0x00000000010000ff, 0x0000000001000000, 0x0000000001000001, 0x0000000001000100,
-    0x0000000001010000, 0x00000001ffff01ff, 0x00000001ff000000, 0x0000000100ff0000,
-    0x000000010000ff00, 0x00000001000000ff, 0x0000000100000000, 0x0000000100000001,
-    0x0000000100000100, 0x0000000100010000, 0x0000000101000000, 0x000001ffff00ff00,
-    0x000001ffff010001, 0x000001ffff0101ff, 0x000001ff00ffff01, 0x000001ff0000ffff,
-    0x000001ff00000000, 0x000001ff010000ff, 0x000001ff01010100, 0x00000100ffff0100,
-    0x00000100ff000000, 0x0000010000ff0000, 0x000001000000ff00, 0x00000100000000ff,
-    0x0000010000000000, 0x0000010000000001, 0x0000010000000100, 0x0000010000010000,
-    0x0000010001000000, 0x000001000101ff01, 0x00000101ffff0001, 0x00000101ff01ffff,
-    0x0000010100000000, 0x0000010101010100, 0x0001ffffff000000, 0x0001ffff00ffffff,
-    0x0001ffff00000100, 0x0001ffff0001ff00, 0x0001ffff01000000, 0x0001ff00ffffff00,
-    0x0001ff00ffff01ff, 0x0001ff00ff010000, 0x0001ff0000000000, 0x0001ff0000010001,
-    0x0001ff0001ff0000, 0x0001ff0001010100, 0x0001ff01ff0000ff, 0x0001ff01ff000001,
-    0x0001ff0100ffffff, 0x0001ff010001ffff, 0x0001ff01000101ff, 0x0001ff010100ff01,
-    0x000100ffff00ffff, 0x000100ffff00ff01, 0x000100ffff000100, 0x000100ff00000000,
-    0x000100ff000101ff, 0x000100ff01ff0101, 0x000100ff0100ffff, 0x000100ff01010101,
-    0x00010000ff000000, 0x00010000ff010100, 0x0001000000ff0000, 0x000100000000ff00,
-    0x00010000000000ff, 0x0001000000000000, 0x0001000000000001, 0x0001000000000100,
-    0x0001000000010000, 0x0001000001ffff01, 0x0001000001000000, 0x0001000100ff0101,
-    0x0001000100000000, 0x00010001010100ff, 0x000101ffffff01ff, 0x000101ffffff0101,
-    0x000101ff00010000, 0x000101ff01ff0000, 0x000101ff0100ff01, 0x00010100ffff0000,
-    0x0001010000000000, 0x000101000001ffff, 0x0001010000010101, 0x00010100010001ff,
-    0x00010101ff00ff00, 0x00010101ff010001, 0x0001010100ffffff, 0x0001010100ff01ff,
-    0x00010101000101ff, 0x0001010101ff0000, 0x000101010100ff01, 0x0001010101000101,
-    0x01ffffffffff0101, 0x01ffffffff01ffff, 0x01ffffffff01ff01, 0x01ffffffff0101ff,
-    0x01ffffffff010101, 0x01ffffff00000000, 0x01ffffff01ff01ff, 0x01ffffff01000101,
-    0x01ffffff0101ff01, 0x01ffffff010100ff, 0x01ffff000000ff00, 0x01ffff0000000001,
-    0x01ffff00000001ff, 0x01ffff0000010000, 0x01ffff0001ff0000, 0x01ffff01ffffffff,
-    0x01ffff01ffff01ff, 0x01ffff01ff000000, 0x01ffff01ff01ffff, 0x01ffff01ff0101ff,
-    0x01ffff010100ffff, 0x01ff00ffffff0000, 0x01ff00ffff010000, 0x01ff00ff00ffff01,
-    0x01ff0000ff0000ff, 0x01ff000000000000, 0x01ff00000001ff01, 0x01ff000001ffffff,
-    0x01ff000001010100, 0x01ff0001ffffff01, 0x01ff0001ff010001, 0x01ff000101ff0100,
-    0x01ff000101000001, 0x01ff0001010100ff, 0x01ff01ffff00ffff, 0x01ff01ff00010001,
-    0x01ff01ff01000000, 0x01ff01ff010101ff, 0x01ff0100ff000001, 0x01ff010000ffff00,
-    0x01ff010000000100, 0x01ff010001ff01ff, 0x01ff01000101ffff, 0x01ff0101ffff00ff,
-    0x01ff0101ffff0101, 0x01ff0101ff0101ff, 0x01ff010100010000, 0x0100ffff00ff00ff,
-    0x0100ffff00ff0001, 0x0100ffff00000100, 0x0100ffff0100ff00, 0x0100ff00ffff0000,
-    0x0100ff00ff00ffff, 0x0100ff00ff00ff01, 0x0100ff00ff000100, 0x0100ff00ff010000,
-    0x0100ff0000000000, 0x0100ff00000100ff, 0x0100ff0001ff0101, 0x0100ff0001010101,
-    0x0100ff0100ff00ff, 0x0100ff0100ff0001, 0x0100ff0100000100, 0x0100ff0100010001,
-    0x0100ff0101000000, 0x010000ffff00ff00, 0x010000ff0000ffff, 0x010000ff00000000,
-    0x010000ff010001ff, 0x010000ff01010001, 0x01000000ffffff00, 0x01000000ffff0101,
-    0x01000000ff000000, 0x01000000ff0100ff, 0x01000000ff010101, 0x0100000000ff0000,
-    0x010000000000ff00, 0x01000000000000ff, 0x0100000000000000, 0x0100000000000001,
-    0x0100000000000100, 0x0100000000010000, 0x0100000001000000, 0x0100000100000000,
-    0x01000001000101ff, 0x0100000101ffff01, 0x010001ffff000101, 0x010001ff00ff0100,
-    0x010001ff0000ff00, 0x010001ff000100ff, 0x010001ff01ffffff, 0x01000100ffff0000,
-    0x01000100ff0001ff, 0x0100010000000000, 0x010001000001ff00, 0x0100010001ff0000,
-    0x01000100010000ff, 0x0100010001000101, 0x01000101ff00ff01, 0x0100010100ff0100,
-    0x010001010000ffff, 0x0100010101010001, 0x0101ffffffff0101, 0x0101ffffff0001ff,
-    0x0101ffffff01ffff, 0x0101ffffff010101, 0x0101ffff00000000, 0x0101ffff0101ffff,
-    0x0101ffff010101ff, 0x0101ff00ff000000, 0x0101ff0000ff0100, 0x0101ff000000ff00,
-    0x0101ff0000010000, 0x0101ff00010000ff, 0x0101ff0001000001, 0x0101ff01ff010101,
-    0x0101ff0100000000, 0x0101ff010101ff00, 0x010100ffffff0000, 0x010100ffff010000,
-    0x010100ff00ff01ff, 0x010100ff000000ff, 0x010100ff00000101, 0x010100ff01ffff00,
-    0x01010000ffffff01, 0x01010000ff000100, 0x01010000ff01ff01, 0x0101000000000000,
-    0x01010000000100ff, 0x010100000101ff01, 0x01010001ffff0000, 0x01010001ff00ffff,
-    0x01010001ff010000, 0x0101000101ffffff, 0x0101000101ff01ff, 0x0101000101010101,
-    0x010101ffff01ffff, 0x010101ff00000000, 0x010101ff0001ff01, 0x010101ff0101ffff,
-    0x010101ff010101ff, 0x01010100ffffffff, 0x01010100ff000001, 0x010101000000ff00,
-    0x0101010001010000, 0x0101010100ff0001, 0x010101010001ff01, 0x010101010101ffff,
-
-};
-
-static const uint8_t ksigns_iq2xs[128] = {
-      0, 129, 130,   3, 132,   5,   6, 135, 136,   9,  10, 139,  12, 141, 142,  15,
-    144,  17,  18, 147,  20, 149, 150,  23,  24, 153, 154,  27, 156,  29,  30, 159,
-    160,  33,  34, 163,  36, 165, 166,  39,  40, 169, 170,  43, 172,  45,  46, 175,
-     48, 177, 178,  51, 180,  53,  54, 183, 184,  57,  58, 187,  60, 189, 190,  63,
-    192,  65,  66, 195,  68, 197, 198,  71,  72, 201, 202,  75, 204,  77,  78, 207,
-     80, 209, 210,  83, 212,  85,  86, 215, 216,  89,  90, 219,  92, 221, 222,  95,
-     96, 225, 226,  99, 228, 101, 102, 231, 232, 105, 106, 235, 108, 237, 238, 111,
-    240, 113, 114, 243, 116, 245, 246, 119, 120, 249, 250, 123, 252, 125, 126, 255,
-};
-
-static const uint8_t kmask_iq2xs[8] = {1, 2, 4, 8, 16, 32, 64, 128};
-
 void dequantize_row_iq2_xxs(const block_iq2_xxs * restrict x, float * restrict y, int k) {
     assert(k % QK_K == 0);
     const int nb = k / QK_K;
@@ -4199,39 +3450,22 @@ void dequantize_row_iq1_s(const block_iq1_s * restrict x, float * restrict y, in
     assert(k % QK_K == 0);
     const int nb = k / QK_K;
 
-    float db[4];
-    uint16_t idx[4];
-    //const int8_t * grid[4];
-
     for (int i = 0; i < nb; i++) {
 
         const float d = GGML_FP16_TO_FP32(x[i].d);
-        const uint8_t * sc = x[i].scales;
-        const uint8_t * qs = x[i].qs;
+        const uint8_t  * qs = x[i].qs;
+        const uint16_t * qh = x[i].qh;
 
-        for (int i8 = 0; i8 < QK_K/8; i8 += 4) {
-            idx[0] = qs[0] | ((sc[0] & 0x08) << 5);
-            idx[1] = qs[1] | ((sc[0] & 0x80) << 1);
-            idx[2] = qs[2] | ((sc[1] & 0x08) << 5);
-            idx[3] = qs[3] | ((sc[1] & 0x80) << 1);
-            //grid[0] = (const int8_t *)(iq1s_grid + (qs[0] | ((sc[0] & 0x08) << 5)));
-            //grid[1] = (const int8_t *)(iq1s_grid + (qs[1] | ((sc[0] & 0x80) << 1)));
-            //grid[2] = (const int8_t *)(iq1s_grid + (qs[2] | ((sc[1] & 0x08) << 5)));
-            //grid[3] = (const int8_t *)(iq1s_grid + (qs[3] | ((sc[1] & 0x80) << 1)));
-            db[0] = d * (2*(sc[0] & 7) + 1);
-            db[1] = d * (2*((sc[0] >> 4) & 7) + 1);
-            db[2] = d * (2*(sc[1] & 7) + 1);
-            db[3] = d * (2*((sc[1] >> 4) & 7) + 1);
+        for (int ib = 0; ib < QK_K/32; ++ib) {
+            const float dl = d * (2*(qh[ib] >> 12) + 1);
             for (int l = 0; l < 4; ++l) {
-                const int8_t * grid = (const int8_t *)(iq1s_grid + idx[l]);
+                const int8_t * grid = (const int8_t *)(iq1s_grid + (qs[l] | (((qh[ib] >> 3*l) & 7) << 8)));
                 for (int j = 0; j < 8; ++j) {
-                    //y[j] = db[l] * grid[l][j];
-                    y[j] = db[l] * grid[j];
+                    y[j] = dl * grid[j];
                 }
                 y += 8;
             }
             qs += 4;
-            sc += 2;
         }
     }
 }
@@ -4809,10 +4043,10 @@ void ggml_vec_dot_q4_1_q8_1(int n, float * restrict s, size_t bs, const void * r
             const int8x16_t y1_h = vld1q_s8(b_y1->qs + 16);
 
             // mmla into int32x4_t
-            float32x4_t scale = {GGML_FP16_TO_FP32(b_x0->d)*GGML_FP16_TO_FP32(b_y0->d),
-                                 GGML_FP16_TO_FP32(b_x0->d)*GGML_FP16_TO_FP32(b_y1->d),
-                                 GGML_FP16_TO_FP32(b_x1->d)*GGML_FP16_TO_FP32(b_y0->d),
-                                 GGML_FP16_TO_FP32(b_x1->d)*GGML_FP16_TO_FP32(b_y1->d)};
+            float32x4_t scale = {GGML_FP16_TO_FP32(b_x0->d)*b_y0->d,
+                                 GGML_FP16_TO_FP32(b_x0->d)*b_y1->d,
+                                 GGML_FP16_TO_FP32(b_x1->d)*b_y0->d,
+                                 GGML_FP16_TO_FP32(b_x1->d)*b_y1->d};
 
             int8x16_t l0 = vreinterpretq_s8_s64(vzip1q_s64(vreinterpretq_s64_s8(x0_l), vreinterpretq_s64_s8(x1_l)));
             int8x16_t l1 = vreinterpretq_s8_s64(vzip2q_s64(vreinterpretq_s64_s8(x0_l), vreinterpretq_s64_s8(x1_l)));
@@ -9759,8 +8993,8 @@ void ggml_vec_dot_iq2_s_q8_K(int n, float * restrict s, size_t bs, const void *
 
     static const uint8_t k_mask2[16] = {0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80,};
 
-    const uint8x16x2_t mask1 = vld1q_u8_x2(k_mask1);
-    const uint8x16_t   mask2 = vld1q_u8(k_mask2);
+    const ggml_uint8x16x2_t mask1 = ggml_vld1q_u8_x2(k_mask1);
+    const uint8x16_t        mask2 = vld1q_u8(k_mask2);
     const uint8x16_t m1 = vdupq_n_u8(1);
     const int32x4_t vzero = vdupq_n_s32(0);
 
@@ -10076,7 +9310,7 @@ void ggml_vec_dot_iq3_xxs_q8_K(int n, float * restrict s, size_t bs, const void
 #endif
 }
 
-void ggml_vec_dot_iq3_s_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc) {
+void ggml_vec_dot_iq3_s_q8_K (int n, float * restrict s, size_t bs, const void * restrict vx, size_t bx, const void * restrict vy, size_t by, int nrc) {
     assert(n % QK_K == 0);
     assert(nrc == 1);
     UNUSED(nrc);
@@ -10104,11 +9338,12 @@ void ggml_vec_dot_iq3_s_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const v
 
     static const int16_t k_shift[8] = {8, 7, 6, 5, 4, 3, 2, 1};
 
-    const uint8x16x2_t mask1  = vld1q_u8_x2(k_mask1);
-    const uint8x16_t   mask2  = vld1q_u8(k_mask2);
-    const int16x8_t    hshift = vld1q_s16(k_shift);
-    const uint16x8_t   m256   = vdupq_n_u16(256);
-    const uint8x16_t   m1     = vdupq_n_u8(1);
+    const ggml_uint8x16x2_t mask1 = ggml_vld1q_u8_x2(k_mask1);
+    const uint8x16_t        mask2 = vld1q_u8(k_mask2);
+
+    const int16x8_t  hshift = vld1q_s16(k_shift);
+    const uint16x8_t m256   = vdupq_n_u16(256);
+    const uint8x16_t m1     = vdupq_n_u8(1);
 
     uint8x16x2_t vs;
     ggml_int8x16x4_t q3s;
@@ -10140,15 +9375,15 @@ void ggml_vec_dot_iq3_s_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const v
 
             const uint8x16_t idx_l = vld1q_u8(qs); qs += 16;
             idx.vec_index = vorrq_u16(vmovl_u8(vget_low_u8 (idx_l)), vandq_u16(vshlq_u16(vdupq_n_u16(qh[ib32+0]), hshift), m256));
-            const uint32x4_t aux32x4_0 = {iq3s_grid[idx.index[0]], iq3s_grid[idx.index[1]],
-                                          iq3s_grid[idx.index[2]], iq3s_grid[idx.index[3]]};
-            const uint32x4_t aux32x4_1 = {iq3s_grid[idx.index[4]], iq3s_grid[idx.index[5]],
-                                          iq3s_grid[idx.index[6]], iq3s_grid[idx.index[7]]};
+            const uint32x4_t aux32x4_0 = ggml_vld1q_u32(iq3s_grid[idx.index[0]], iq3s_grid[idx.index[1]],
+                                                        iq3s_grid[idx.index[2]], iq3s_grid[idx.index[3]]);
+            const uint32x4_t aux32x4_1 = ggml_vld1q_u32(iq3s_grid[idx.index[4]], iq3s_grid[idx.index[5]],
+                                                        iq3s_grid[idx.index[6]], iq3s_grid[idx.index[7]]);
             idx.vec_index = vorrq_u16(vmovl_u8(vget_high_u8(idx_l)), vandq_u16(vshlq_u16(vdupq_n_u16(qh[ib32+1]), hshift), m256));
-            const uint32x4_t aux32x4_2 = {iq3s_grid[idx.index[0]], iq3s_grid[idx.index[1]],
-                                          iq3s_grid[idx.index[2]], iq3s_grid[idx.index[3]]};
-            const uint32x4_t aux32x4_3 = {iq3s_grid[idx.index[4]], iq3s_grid[idx.index[5]],
-                                          iq3s_grid[idx.index[6]], iq3s_grid[idx.index[7]]};
+            const uint32x4_t aux32x4_2 = ggml_vld1q_u32(iq3s_grid[idx.index[0]], iq3s_grid[idx.index[1]],
+                                                        iq3s_grid[idx.index[2]], iq3s_grid[idx.index[3]]);
+            const uint32x4_t aux32x4_3 = ggml_vld1q_u32(iq3s_grid[idx.index[4]], iq3s_grid[idx.index[5]],
+                                                        iq3s_grid[idx.index[6]], iq3s_grid[idx.index[7]]);
 
 
             vs.val[0] = vreinterpretq_u8_u32(vdupq_n_u32(signs[0] | (signs[1] << 16)));
@@ -10323,7 +9558,7 @@ static inline __m256i mul_add_epi8(const __m256i x, const __m256i y) {
 }
 #endif
 
-void ggml_vec_dot_iq1_s_q8_K  (int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc) {
+void ggml_vec_dot_iq1_s_q8_K  (int n, float * restrict s, size_t bs, const void * restrict vx, size_t bx, const void * restrict vy, size_t by, int nrc) {
     assert(n % QK_K == 0);
     assert(nrc == 1);
     UNUSED(nrc);
@@ -10336,113 +9571,72 @@ void ggml_vec_dot_iq1_s_q8_K  (int n, float * GGML_RESTRICT s, size_t bs, const
 
     const int nb = n / QK_K;
 
-    // TODO: implement for QK_K = 64
-#if defined __ARM_NEON && QK_K == 256
+#if defined __ARM_NEON
 
-    const uint8x16_t m8 = vdupq_n_u8(0x08);
-    const uint8x16_t m7 = vdupq_n_u8(0x07);
-    const uint8x16_t m1 = vdupq_n_u8(0x01);
-    const int32x4_t vzero = vdupq_n_s32(0);
-
-    uint16_t gindex[8];
-    uint16x8x2_t vindex;
-    int8x16x4_t q1b;
+    ggml_int8x16x4_t q1b;
     ggml_int8x16x4_t q8b;
-    uint16x8x4_t scales;
-    int32x4x2_t sumi;
-    int32x4x2_t dotq;
 
     float sumf = 0;
     for (int i = 0; i < nb; ++i) {
 
-        const int8_t  * q8 = y[i].qs;
-        const uint8_t * qs = x[i].qs;
-        const uint8_t * sc = x[i].scales;
+        const int8_t   * q8 = y[i].qs;
+        const uint8_t  * qs = x[i].qs;
+        const uint16_t * qh = x[i].qh;
 
-        sumi.val[0] = sumi.val[1] = vzero;
+        int sumi1 = 0, sumi2 = 0;
 
-        for (int i128 = 0; i128 < QK_K/128; ++i128) {
-            const uint8x16_t ql = vld1q_u8(qs); qs += 16;
-            const uint8x8_t tm1 = vld1_u8 (sc); sc +=  8;
-            const uint8x8_t tm2 = vshr_n_u8(tm1, 4);
-            const uint8x16_t qh = vcombine_u8(vzip1_u8(tm1, tm2), vzip2_u8(tm1, tm2));
-            const uint8x16_t hbit = vandq_u8(qh, m8);
-            vindex.val[0] = vorrq_u16(vmovl_u8(vget_low_u8 (ql)), vshlq_n_u16(vmovl_u8(vget_low_u8 (hbit)), 5));
-            vindex.val[1] = vorrq_u16(vmovl_u8(vget_high_u8(ql)), vshlq_n_u16(vmovl_u8(vget_high_u8(hbit)), 5));
-            const uint8x16_t scales8 = vorrq_u8(vshlq_n_u8(vandq_u8(qh, m7), 1), m1);
-            scales.val[0] = vmovl_u8(vget_low_u8 (scales8));
-            scales.val[1] = vmovl_u8(vget_high_u8 (scales8));
+        for (int ib = 0; ib < QK_K/32; ib += 2) {
 
-            for (int l = 0; l < 2; ++l) {
-                vst1q_u16(gindex+0, vindex.val[l]);
-                q1b.val[0] = vcombine_s8(vld1_s8((const void *)(iq1s_grid+gindex[0])), vld1_s8((const void *)(iq1s_grid+gindex[1])));
-                q1b.val[1] = vcombine_s8(vld1_s8((const void *)(iq1s_grid+gindex[2])), vld1_s8((const void *)(iq1s_grid+gindex[3])));
-                q1b.val[2] = vcombine_s8(vld1_s8((const void *)(iq1s_grid+gindex[4])), vld1_s8((const void *)(iq1s_grid+gindex[5])));
-                q1b.val[3] = vcombine_s8(vld1_s8((const void *)(iq1s_grid+gindex[6])), vld1_s8((const void *)(iq1s_grid+gindex[7])));
-                q8b = ggml_vld1q_s8_x4(q8); q8 += 64;
+            q1b.val[0] = vcombine_s8(vld1_s8((const int8_t *)(iq1s_grid + (qs[0] | ((qh[ib+0] << 8) & 0x700)))),
+                                     vld1_s8((const int8_t *)(iq1s_grid + (qs[1] | ((qh[ib+0] << 5) & 0x700)))));
+            q1b.val[1] = vcombine_s8(vld1_s8((const int8_t *)(iq1s_grid + (qs[2] | ((qh[ib+0] << 2) & 0x700)))),
+                                     vld1_s8((const int8_t *)(iq1s_grid + (qs[3] | ((qh[ib+0] >> 1) & 0x700)))));
+            q1b.val[2] = vcombine_s8(vld1_s8((const int8_t *)(iq1s_grid + (qs[4] | ((qh[ib+1] << 8) & 0x700)))),
+                                     vld1_s8((const int8_t *)(iq1s_grid + (qs[5] | ((qh[ib+1] << 5) & 0x700)))));
+            q1b.val[3] = vcombine_s8(vld1_s8((const int8_t *)(iq1s_grid + (qs[6] | ((qh[ib+1] << 2) & 0x700)))),
+                                     vld1_s8((const int8_t *)(iq1s_grid + (qs[7] | ((qh[ib+1] >> 1) & 0x700)))));
+            qs += 8;
 
-                dotq.val[0] = vpaddq_s32(ggml_vdotq_s32(vzero, q1b.val[0], q8b.val[0]), ggml_vdotq_s32(vzero, q1b.val[1], q8b.val[1]));
-                dotq.val[1] = vpaddq_s32(ggml_vdotq_s32(vzero, q1b.val[2], q8b.val[2]), ggml_vdotq_s32(vzero, q1b.val[3], q8b.val[3]));
+            q8b = ggml_vld1q_s8_x4(q8); q8 += 64;
+
+            const int32x4_t p1 = ggml_vdotq_s32(ggml_vdotq_s32(vdupq_n_s32(0), q1b.val[0], q8b.val[0]), q1b.val[1], q8b.val[1]);
+            const int32x4_t p2 = ggml_vdotq_s32(ggml_vdotq_s32(vdupq_n_s32(0), q1b.val[2], q8b.val[2]), q1b.val[3], q8b.val[3]);
+
+            sumi1 += vaddvq_s32(p1) * (2*(qh[ib+0] >> 12) + 1);
+            sumi2 += vaddvq_s32(p2) * (2*(qh[ib+1] >> 12) + 1);
 
-                sumi.val[0] = vmlaq_s32(sumi.val[0], dotq.val[0], vreinterpretq_s32_u32(vmovl_u16(vget_low_u16 (scales.val[l]))));
-                sumi.val[1] = vmlaq_s32(sumi.val[1], dotq.val[1], vreinterpretq_s32_u32(vmovl_u16(vget_high_u16(scales.val[l]))));
-            }
         }
 
-        sumf += y[i].d * GGML_FP16_TO_FP32(x[i].d) * vaddvq_s32(vaddq_s32(sumi.val[0], sumi.val[1]));
+        sumf += y[i].d * GGML_FP16_TO_FP32(x[i].d) * (sumi1 + sumi2);
     }
 
     *s = sumf;
 
-    // TODO: implement for QK_K = 64
-#elif defined __AVX2__ && QK_K == 256
-
-    const __m128i m8 = _mm_set1_epi8(0x08);
-    const __m128i m7 = _mm_set1_epi8(0x07);
-    const __m128i m1 = _mm_set1_epi8(0x01);
-    const __m128i shuffle_h = _mm_set_epi8(15, 7, 14, 6, 13, 5, 12, 4, 11, 3, 10, 2, 9, 1, 8, 0);
-    const __m128i shuffle_s[4] = {
-        _mm_set_epi32(0x03030303, 0x02020202, 0x01010101, 0x00000000),
-        _mm_set_epi32(0x07070707, 0x06060606, 0x05050505, 0x04040404),
-        _mm_set_epi32(0x0b0b0b0b, 0x0a0a0a0a, 0x09090909, 0x08080808),
-        _mm_set_epi32(0x0f0f0f0f, 0x0e0e0e0e, 0x0d0d0d0d, 0x0c0c0c0c)
-    };
-
-    uint64_t aux64;
-
-    typedef union m256i_uint16 {
-        __m256i reg;
-        uint16_t s[16];
-    } m256i_uint16_t;
-
-    m256i_uint16_t v_gindex;
+#elif defined __AVX2__
 
     __m256 accum = _mm256_setzero_ps();
     for (int i = 0; i < nb; ++i) {
 
-        const int8_t  * q8 = y[i].qs;
-        const uint8_t * qs = x[i].qs;
-        const uint8_t * sc = x[i].scales;
+        const int8_t   * q8 = y[i].qs;
+        const uint8_t  * qs = x[i].qs;
+        const uint16_t * qh = x[i].qh;
 
         __m256i sumi = _mm256_setzero_si256();
-        for (int i128 = 0; i128 < QK_K/128; ++i128) {
-            const __m128i ql = _mm_loadu_si128((const __m128i*)qs); qs += 16;
-            memcpy(&aux64, sc, 8); sc += 8;
-            const __m128i qh = _mm_shuffle_epi8(_mm_set_epi64x(aux64 >> 4, aux64), shuffle_h);
-            const __m256i hbit = _mm256_cvtepu8_epi16(_mm_and_si128(qh, m8));
-            v_gindex.reg = _mm256_or_si256(_mm256_cvtepu8_epi16(ql), _mm256_slli_epi16(hbit, 5));
-            const __m128i scales = _mm_or_si128(_mm_slli_epi16(_mm_and_si128(qh, m7), 1), m1);
+        for (int ib = 0; ib < QK_K/32; ib += 2) {
+            const __m256i q1b_1 = _mm256_set_epi64x(iq1s_grid[qs[3] | ((qh[ib+0] >> 1) & 0x700)], iq1s_grid[qs[2] | ((qh[ib+0] << 2) & 0x700)],
+                                                    iq1s_grid[qs[1] | ((qh[ib+0] << 5) & 0x700)], iq1s_grid[qs[0] | ((qh[ib+0] << 8) & 0x700)]);
+            const __m256i q1b_2 = _mm256_set_epi64x(iq1s_grid[qs[7] | ((qh[ib+1] >> 1) & 0x700)], iq1s_grid[qs[6] | ((qh[ib+1] << 2) & 0x700)],
+                                                    iq1s_grid[qs[5] | ((qh[ib+1] << 5) & 0x700)], iq1s_grid[qs[4] | ((qh[ib+1] << 8) & 0x700)]);
+            qs += 8;
+            const __m256i q8b_1 = _mm256_loadu_si256((const __m256i*)q8); q8 += 32;
+            const __m256i q8b_2 = _mm256_loadu_si256((const __m256i*)q8); q8 += 32;
 
-            for (int i32 = 0; i32 < 4; ++i32) {
-                const __m256i q8b = _mm256_loadu_si256((const __m256i*)q8); q8 += 32;
-                const __m256i q1b = _mm256_set_epi64x(iq1s_grid[v_gindex.s[4*i32+3]], iq1s_grid[v_gindex.s[4*i32+2]],
-                                                      iq1s_grid[v_gindex.s[4*i32+1]], iq1s_grid[v_gindex.s[4*i32+0]]);
-                const __m256i dot = mul_add_epi8(q1b, q8b);
-                const __m256i s16 = _mm256_cvtepi8_epi16(_mm_shuffle_epi8(scales, shuffle_s[i32]));
-                const __m256i p   = _mm256_madd_epi16(s16, dot);
-                sumi = _mm256_add_epi32(sumi, p);
-            }
+            const __m256i dot1 = mul_add_epi8(q1b_1, q8b_1);
+            const __m256i dot2 = mul_add_epi8(q1b_2, q8b_2);
+            const __m256i p1 = _mm256_madd_epi16(dot1, _mm256_set1_epi16(2*(qh[ib+0] >> 12) + 1));
+            const __m256i p2 = _mm256_madd_epi16(dot2, _mm256_set1_epi16(2*(qh[ib+1] >> 12) + 1));
 
+            sumi = _mm256_add_epi32(sumi, _mm256_add_epi32(p1, p2));
         }
 
         accum = _mm256_fmadd_ps(_mm256_set1_ps(y[i].d * GGML_FP16_TO_FP32(x[i].d)), _mm256_cvtepi32_ps(sumi), accum);
@@ -10453,35 +9647,26 @@ void ggml_vec_dot_iq1_s_q8_K  (int n, float * GGML_RESTRICT s, size_t bs, const
 
 #else
 
-    int db[4];
-    uint16_t idx[4];
-
     float sumf = 0;
-    for (int i = 0; i < nb; ++i) {
+    for (int i = 0; i < nb; i++) {
 
-        const int8_t  * q8 = y[i].qs;
-        const uint8_t * qs = x[i].qs;
-        const uint8_t * sc = x[i].scales;
+        const int8_t   * q8 = y[i].qs;
+        const uint8_t  * qs = x[i].qs;
+        const uint16_t * qh = x[i].qh;
 
         int sumi = 0;
-        for (int i32 = 0; i32 < QK_K/32; ++i32) {
-            idx[0] = qs[0] | ((sc[0] & 0x08) << 5);
-            idx[1] = qs[1] | ((sc[0] & 0x80) << 1);
-            idx[2] = qs[2] | ((sc[1] & 0x08) << 5);
-            idx[3] = qs[3] | ((sc[1] & 0x80) << 1);
-            db[0] = (2*(sc[0] & 7) + 1);
-            db[1] = (2*((sc[0] >> 4) & 7) + 1);
-            db[2] = (2*(sc[1] & 7) + 1);
-            db[3] = (2*((sc[1] >> 4) & 7) + 1);
+        for (int ib = 0; ib < QK_K/32; ++ib) {
+            const int ls = 2*(qh[ib] >> 12) + 1;
+            int lsum = 0;
             for (int l = 0; l < 4; ++l) {
-                const int8_t * grid = (const int8_t *)(iq1s_grid + idx[l]);
-                int suml = 0;
-                for (int j = 0; j < 8; ++j) suml += q8[j] * grid[j];
-                sumi += db[l] * suml;
+                const int8_t * grid = (const int8_t *)(iq1s_grid + (qs[l] | (((qh[ib] >> 3*l) & 7) << 8)));
+                for (int j = 0; j < 8; ++j) {
+                    lsum += q8[j] * grid[j];
+                }
                 q8 += 8;
             }
+            sumi += ls * lsum;
             qs += 4;
-            sc += 2;
         }
 
         sumf += GGML_FP16_TO_FP32(x[i].d) * y[i].d * sumi;
@@ -10745,7 +9930,7 @@ static inline int iq2_grid_size(enum ggml_type type) {
     GGML_ASSERT(type == GGML_TYPE_IQ2_XXS || type == GGML_TYPE_IQ2_XS || type == GGML_TYPE_IQ1_S || type == GGML_TYPE_IQ2_S);
     return type == GGML_TYPE_IQ2_XXS ? 256 :
            type == GGML_TYPE_IQ2_XS  ? 512 :
-           type == GGML_TYPE_IQ1_S   ? 512 : 1024;
+           type == GGML_TYPE_IQ1_S   ? NGRID_IQ1S : 1024;
 }
 
 static int iq2_compare_func(const void * left, const void * right) {
@@ -10812,39 +9997,135 @@ void iq2xs_init_impl(enum ggml_type type) {
         40962, 40968, 40970, 40992, 41002, 41120, 41297, 41305, 41382, 41472, 41474, 41480, 41514, 41600, 41632, 42048,
         42133, 42597, 42648, 43018, 43040, 43042, 43048, 43168, 43176, 43268, 43396, 43398, 43560, 43562, 43665, 43690,
     };
-    static const uint16_t kgrid_1bit_512[512] = {
-           10,    33,    41,    85,   132,   134,   160,   162,   277,   337,   340,   345,   357,   405,   516,   545,
-          553,   598,   641,   650,   681,  1042,  1044,  1097,  1169,  1176,  1320,  1345,  1365,  1378,  1434,  1444,
-         1545,  1617,  1642,  1685,  2053,  2080,  2089,  2133,  2176,  2182,  2208,  2214,  2306,  2384,  2393,  2440,
-         2453,  2581,  2664,  2690,  2721,  4117,  4161,  4182,  4184,  4261,  4357,  4369,  4372,  4377,  4390,  4422,
-         4432,  4437,  4449,  4457,  4485,  4497,  4505,  4629,  4677,  4696,  4774,  5205,  5217,  5225,  5386,  5397,
-         5409,  5445,  5457,  5460,  5461,  5462,  5465,  5472,  5477,  5525,  5545,  5650,  5668,  5717,  5729,  5769,
-         5777,  6212,  6234,  6244,  6293,  6424,  6482,  6485,  6502,  6505,  6529,  6538,  6565,  6656,  6682,  6788,
-         6806,  6820,  8218,  8224,  8226,  8232,  8277,  8326,  8354,  8469,  8521,  8530,  8549,  8596,  8737,  8794,
-         9221,  9253,  9348,  9369,  9380,  9474,  9557,  9633,  9732,  9753,  9793,  9830,  9862,  9880, 10240, 10272,
-        10282, 10321, 10406, 10517, 10530, 10566, 10585, 10645, 10896, 16466, 16468, 16473, 16485, 16646, 16660, 16665,
-        16725, 16793, 16806, 16914, 16969, 16977, 16996, 17028, 17057, 17408, 17416, 17434, 17493, 17512, 17578, 17685,
-        17696, 17733, 17745, 17748, 17749, 17750, 17753, 17765, 17794, 17813, 17946, 17984, 18005, 18072, 18453, 18529,
-        18569, 18722, 18756, 18762, 18773, 18794, 18833, 18853, 18945, 19026, 19033, 19077, 20489, 20497, 20500, 20517,
-        20565, 20586, 20610, 20633, 20757, 20769, 20776, 20805, 20817, 20820, 20821, 20822, 20825, 20837, 20864, 20872,
-        20885, 20896, 21002, 21029, 21077, 21146, 21510, 21525, 21573, 21585, 21588, 21589, 21590, 21593, 21605, 21653,
-        21665, 21765, 21777, 21780, 21781, 21782, 21785, 21797, 21825, 21828, 21829, 21830, 21833, 21840, 21841, 21842,
-        21844, 21846, 21848, 21849, 21850, 21857, 21860, 21861, 21862, 21865, 21893, 21905, 21908, 21909, 21910, 21913,
-        21925, 22024, 22037, 22085, 22097, 22100, 22101, 22102, 22105, 22117, 22165, 22545, 22566, 22568, 22594, 22608,
-        22613, 22676, 22697, 22793, 22805, 22853, 22865, 22868, 22869, 22870, 22873, 22885, 22933, 22946, 23046, 23072,
-        23125, 23209, 24597, 24640, 24665, 24673, 24725, 24833, 24840, 24869, 24917, 24934, 24965, 25001, 25108, 25110,
-        25152, 25184, 25192, 25234, 25616, 25618, 25625, 25685, 25704, 25738, 25744, 25770, 25877, 25897, 25925, 25937,
-        25940, 25941, 25942, 25945, 25957, 25986, 26005, 26186, 26197, 26276, 26632, 26634, 26725, 26757, 26770, 26885,
-        26965, 26976, 26986, 27032, 27153, 27174, 27200, 27208, 27240, 27269, 27282, 27290, 32778, 32800, 32802, 32808,
-        32810, 32853, 32904, 32922, 32930, 32932, 33105, 33110, 33112, 33125, 33157, 33280, 33288, 33301, 33312, 33320,
-        33424, 33797, 33829, 33858, 34068, 34133, 34146, 34176, 34217, 34306, 34342, 34441, 34454, 34468, 34832, 34918,
-        34965, 34984, 35094, 35137, 35161, 35208, 35232, 35332, 35338, 35368, 35429, 36932, 36934, 36953, 37009, 37125,
-        37136, 37138, 37145, 37157, 37205, 37220, 37258, 37290, 37444, 37446, 37465, 37478, 37525, 37905, 37968, 37973,
-        38040, 38054, 38145, 38154, 38165, 38180, 38186, 38213, 38225, 38228, 38229, 38230, 38233, 38245, 38293, 38485,
-        38504, 38530, 38938, 38985, 38993, 39012, 39040, 39173, 39192, 39253, 39265, 39301, 39316, 39322, 39442, 39497,
-        39504, 39590, 40970, 40984, 40992, 41002, 41045, 41120, 41128, 41237, 41289, 41297, 41317, 41364, 41366, 41514,
-        41557, 41633, 41989, 42021, 42056, 42068, 42074, 42113, 42242, 42265, 42274, 42325, 42340, 42402, 42501, 42512,
-        42533, 42624, 42632, 42666, 43040, 43093, 43106, 43168, 43176, 43264, 43286, 43345, 43429, 43590, 43618, 43680,
+    static const uint16_t kgrid_1bit_2048[NGRID_IQ1S] = {
+            0,     2,     5,     8,    10,    17,    21,    32,    34,    40,    42,    69,    81,    84,    86,   101,
+          128,   130,   136,   138,   149,   160,   162,   168,   170,   260,   261,   273,   276,   278,   281,   282,
+          293,   321,   326,   329,   338,   341,   346,   353,   356,   358,   360,   389,   401,   404,   406,   421,
+          512,   514,   520,   522,   533,   544,   546,   552,   554,   581,   593,   601,   612,   617,   640,   642,
+          648,   650,   657,   661,   665,   672,   674,   680,   682,  1041,  1044,  1046,  1061,  1089,  1097,  1109,
+         1114,  1124,  1125,  1169,  1177,  1189,  1281,  1284,  1285,  1286,  1301,  1304,  1306,  1321,  1344,  1349,
+         1354,  1360,  1361,  1364,  1365,  1366,  1369,  1376,  1378,  1381,  1384,  1386,  1409,  1425,  1429,  1432,
+         1434,  1441,  1444,  1445,  1446,  1449,  1556,  1561,  1601,  1604,  1616,  1618,  1621,  1624,  1632,  1633,
+         1638,  1641,  1669,  1681,  1684,  1689,  2048,  2050,  2056,  2058,  2069,  2080,  2082,  2088,  2090,  2117,
+         2129,  2134,  2149,  2176,  2178,  2184,  2186,  2197,  2208,  2210,  2216,  2218,  2309,  2321,  2324,  2329,
+         2340,  2341,  2369,  2384,  2385,  2389,  2401,  2404,  2409,  2449,  2452,  2454,  2457,  2469,  2560,  2562,
+         2568,  2570,  2581,  2592,  2594,  2600,  2602,  2629,  2641,  2649,  2657,  2661,  2688,  2690,  2693,  2696,
+         2698,  2709,  2720,  2722,  2728,  2730,  4112,  4113,  4116,  4121,  4132,  4133,  4161,  4164,  4176,  4181,
+         4184,  4193,  4196,  4197,  4201,  4241,  4244,  4246,  4257,  4261,  4353,  4356,  4358,  4361,  4368,  4370,
+         4373,  4376,  4385,  4388,  4393,  4421,  4426,  4432,  4433,  4434,  4436,  4437,  4438,  4441,  4448,  4453,
+         4484,  4498,  4501,  4513,  4516,  4625,  4628,  4630,  4645,  4672,  4678,  4681,  4690,  4693,  4696,  4698,
+         4708,  4710,  4741,  4753,  4756,  4758,  4773,  5121,  5126,  5129,  5140,  5141,  5144,  5145,  5153,  5158,
+         5185,  5189,  5190,  5192,  5194,  5201,  5204,  5205,  5206,  5209,  5218,  5221,  5224,  5252,  5257,  5264,
+         5268,  5269,  5272,  5273,  5274,  5281,  5284,  5285,  5289,  5378,  5381,  5386,  5393,  5396,  5397,  5398,
+         5401,  5408,  5410,  5413,  5416,  5418,  5441,  5444,  5445,  5446,  5457,  5458,  5460,  5461,  5462,  5465,
+         5466,  5473,  5476,  5477,  5478,  5481,  5504,  5506,  5508,  5509,  5512,  5514,  5520,  5521,  5524,  5525,
+         5526,  5529,  5530,  5536,  5538,  5541,  5633,  5636,  5637,  5638,  5653,  5654,  5656,  5658,  5665,  5670,
+         5696,  5698,  5700,  5701,  5704,  5706,  5713,  5717,  5718,  5720,  5721,  5729,  5732,  5733,  5736,  5737,
+         5738,  5766,  5770,  5778,  5781,  5796,  5801,  6161,  6166,  6181,  6209,  6212,  6214,  6217,  6224,  6229,
+         6232,  6234,  6240,  6241,  6244,  6246,  6249,  6277,  6289,  6292,  6309,  6416,  6418,  6421,  6426,  6433,
+         6437,  6466,  6468,  6469,  6472,  6481,  6484,  6485,  6486,  6489,  6490,  6496,  6501,  6506,  6537,  6545,
+         6546,  6549,  6552,  6561,  6566,  6569,  6665,  6678,  6692,  6694,  6724,  6726,  6729,  6736,  6738,  6741,
+         6744,  6753,  6758,  6761,  6789,  6801,  6806,  6810,  8192,  8194,  8200,  8202,  8213,  8224,  8226,  8229,
+         8232,  8234,  8261,  8273,  8281,  8289,  8293,  8320,  8322,  8328,  8330,  8341,  8352,  8354,  8357,  8360,
+         8362,  8453,  8465,  8468,  8473,  8485,  8514,  8516,  8521,  8533,  8536,  8538,  8545,  8548,  8549,  8550,
+         8581,  8592,  8598,  8601,  8613,  8705,  8712,  8714,  8721,  8725,  8736,  8738,  8744,  8746,  8773,  8785,
+         8790,  8793,  8805,  8833,  8840,  8842,  8849,  8853,  8864,  8866,  8872,  8874,  9221,  9236,  9238,  9241,
+         9253,  9284,  9285,  9286,  9289,  9298,  9301,  9304,  9306,  9318,  9349,  9361,  9364,  9369,  9377,  9381,
+         9481,  9493,  9505,  9513,  9536,  9541,  9544,  9553,  9556,  9557,  9561,  9570,  9573,  9576,  9609,  9616,
+         9620,  9621,  9624,  9626,  9633,  9636,  9638,  9641,  9733,  9744,  9746,  9753,  9765,  9793,  9801,  9813,
+         9824,  9825,  9833,  9860,  9862,  9872,  9882, 10240, 10242, 10248, 10250, 10261, 10272, 10274, 10280, 10282,
+        10309, 10321, 10324, 10341, 10368, 10370, 10376, 10378, 10400, 10402, 10408, 10410, 10505, 10513, 10516, 10521,
+        10533, 10566, 10569, 10578, 10581, 10593, 10596, 10598, 10601, 10629, 10640, 10646, 10649, 10660, 10661, 10752,
+        10754, 10760, 10762, 10784, 10786, 10792, 10794, 10821, 10833, 10838, 10841, 10853, 10880, 10882, 10888, 10890,
+        10901, 10912, 10914, 10920, 10922, 16389, 16401, 16406, 16421, 16457, 16466, 16469, 16472, 16474, 16481, 16484,
+        16486, 16532, 16537, 16545, 16550, 16640, 16641, 16644, 16646, 16649, 16658, 16661, 16662, 16664, 16666, 16673,
+        16678, 16681, 16709, 16712, 16714, 16721, 16724, 16725, 16726, 16729, 16730, 16741, 16744, 16746, 16769, 16772,
+        16774, 16784, 16786, 16789, 16800, 16801, 16802, 16901, 16913, 16916, 16918, 16933, 16961, 16978, 16981, 16986,
+        16996, 17001, 17033, 17044, 17061, 17409, 17429, 17433, 17449, 17477, 17480, 17482, 17489, 17492, 17493, 17494,
+        17505, 17506, 17509, 17512, 17514, 17537, 17542, 17545, 17552, 17554, 17557, 17568, 17569, 17577, 17665, 17666,
+        17669, 17674, 17681, 17684, 17685, 17686, 17689, 17696, 17701, 17706, 17729, 17732, 17733, 17734, 17737, 17744,
+        17745, 17748, 17749, 17750, 17752, 17753, 17761, 17764, 17765, 17766, 17769, 17794, 17796, 17797, 17800, 17809,
+        17812, 17813, 17814, 17817, 17818, 17829, 17832, 17834, 17921, 17925, 17929, 17940, 17941, 17944, 17946, 17953,
+        17956, 17961, 17984, 17986, 17989, 17992, 18000, 18001, 18002, 18005, 18006, 18009, 18018, 18021, 18024, 18049,
+        18053, 18058, 18068, 18069, 18081, 18084, 18086, 18437, 18449, 18453, 18458, 18469, 18498, 18505, 18512, 18517,
+        18520, 18529, 18532, 18534, 18537, 18565, 18577, 18580, 18582, 18585, 18597, 18689, 18693, 18694, 18698, 18704,
+        18708, 18709, 18712, 18721, 18724, 18726, 18752, 18757, 18762, 18769, 18770, 18772, 18773, 18774, 18777, 18784,
+        18786, 18789, 18790, 18794, 18822, 18825, 18834, 18837, 18838, 18840, 18849, 18852, 18854, 18857, 18966, 19012,
+        19014, 19017, 19029, 19032, 19034, 19044, 19049, 19092, 19109, 20481, 20484, 20485, 20486, 20489, 20498, 20501,
+        20506, 20513, 20516, 20521, 20544, 20549, 20552, 20561, 20564, 20565, 20566, 20569, 20581, 20584, 20614, 20617,
+        20629, 20632, 20640, 20641, 20646, 20649, 20741, 20744, 20745, 20746, 20753, 20756, 20757, 20758, 20760, 20761,
+        20768, 20773, 20774, 20776, 20778, 20801, 20804, 20805, 20806, 20809, 20816, 20817, 20818, 20820, 20821, 20822,
+        20824, 20825, 20826, 20833, 20836, 20837, 20838, 20841, 20866, 20869, 20881, 20884, 20885, 20886, 20889, 20896,
+        20901, 20906, 20993, 20998, 21010, 21013, 21018, 21025, 21028, 21058, 21061, 21066, 21073, 21076, 21077, 21078,
+        21081, 21090, 21093, 21125, 21136, 21138, 21141, 21145, 21146, 21156, 21508, 21509, 21521, 21524, 21525, 21526,
+        21528, 21529, 21537, 21541, 21544, 21546, 21569, 21572, 21573, 21574, 21577, 21578, 21584, 21585, 21588, 21589,
+        21590, 21592, 21593, 21594, 21601, 21602, 21604, 21605, 21606, 21609, 21632, 21640, 21642, 21649, 21652, 21653,
+        21654, 21657, 21665, 21668, 21669, 21674, 21761, 21762, 21764, 21765, 21766, 21769, 21776, 21777, 21778, 21780,
+        21781, 21782, 21785, 21786, 21793, 21796, 21797, 21798, 21801, 21824, 21825, 21826, 21828, 21829, 21830, 21832,
+        21833, 21840, 21841, 21842, 21844, 21845, 21846, 21848, 21849, 21850, 21856, 21857, 21860, 21861, 21862, 21864,
+        21865, 21866, 21889, 21892, 21893, 21897, 21898, 21904, 21905, 21908, 21909, 21910, 21912, 21913, 21921, 21924,
+        21925, 21926, 21929, 22016, 22017, 22018, 22020, 22022, 22024, 22025, 22033, 22036, 22037, 22040, 22041, 22048,
+        22049, 22050, 22052, 22053, 22054, 22056, 22057, 22081, 22085, 22086, 22088, 22089, 22090, 22096, 22097, 22098,
+        22100, 22101, 22102, 22104, 22105, 22106, 22113, 22116, 22117, 22121, 22146, 22149, 22150, 22152, 22153, 22154,
+        22161, 22165, 22170, 22178, 22181, 22182, 22184, 22185, 22532, 22533, 22534, 22537, 22544, 22549, 22552, 22561,
+        22570, 22597, 22600, 22602, 22609, 22612, 22613, 22614, 22616, 22617, 22624, 22626, 22628, 22629, 22658, 22665,
+        22672, 22674, 22677, 22680, 22689, 22697, 22785, 22786, 22789, 22794, 22801, 22804, 22805, 22806, 22809, 22821,
+        22849, 22852, 22853, 22854, 22857, 22864, 22865, 22866, 22868, 22869, 22870, 22872, 22873, 22874, 22881, 22884,
+        22885, 22886, 22889, 22913, 22917, 22921, 22929, 22932, 22933, 22934, 22936, 22937, 22949, 23044, 23048, 23061,
+        23066, 23072, 23077, 23078, 23081, 23109, 23112, 23113, 23121, 23125, 23126, 23128, 23129, 23138, 23141, 23144,
+        23146, 23169, 23178, 23186, 23189, 23190, 23192, 23194, 23201, 24581, 24596, 24598, 24601, 24613, 24644, 24656,
+        24661, 24662, 24664, 24666, 24673, 24676, 24678, 24681, 24705, 24726, 24741, 24833, 24836, 24838, 24841, 24850,
+        24853, 24865, 24866, 24870, 24873, 24901, 24905, 24913, 24917, 24918, 24921, 24933, 24934, 24938, 24964, 24970,
+        24978, 24981, 24993, 24998, 25001, 25105, 25110, 25113, 25152, 25153, 25158, 25173, 25174, 25176, 25184, 25221,
+        25233, 25238, 25253, 25617, 25618, 25621, 25622, 25626, 25633, 25638, 25641, 25664, 25666, 25669, 25672, 25674,
+        25681, 25684, 25685, 25686, 25689, 25690, 25696, 25698, 25701, 25732, 25733, 25737, 25744, 25746, 25748, 25749,
+        25750, 25752, 25754, 25761, 25764, 25769, 25861, 25864, 25866, 25873, 25877, 25878, 25881, 25924, 25925, 25926,
+        25929, 25936, 25937, 25940, 25941, 25942, 25945, 25953, 25956, 25957, 25958, 25961, 25990, 25993, 25994, 26001,
+        26005, 26006, 26009, 26010, 26018, 26021, 26022, 26024, 26114, 26121, 26133, 26144, 26150, 26152, 26153, 26176,
+        26181, 26184, 26186, 26193, 26196, 26197, 26198, 26200, 26202, 26208, 26213, 26216, 26240, 26242, 26245, 26250,
+        26260, 26262, 26264, 26265, 26272, 26276, 26278, 26282, 26646, 26649, 26661, 26689, 26706, 26709, 26714, 26721,
+        26729, 26757, 26769, 26776, 26790, 26881, 26884, 26896, 26901, 26913, 26916, 26918, 26921, 26944, 26945, 26949,
+        26950, 26952, 26961, 26964, 26965, 26966, 26969, 26976, 26981, 26986, 27010, 27012, 27018, 27029, 27041, 27044,
+        27045, 27049, 27153, 27158, 27160, 27201, 27204, 27209, 27216, 27221, 27224, 27226, 27236, 27237, 27241, 27270,
+        27284, 27288, 27290, 27302, 32768, 32770, 32776, 32778, 32800, 32802, 32808, 32810, 32837, 32848, 32849, 32852,
+        32854, 32857, 32869, 32896, 32898, 32904, 32906, 32917, 32928, 32930, 32936, 32938, 33029, 33041, 33044, 33046,
+        33049, 33061, 33089, 33092, 33097, 33104, 33106, 33109, 33110, 33112, 33113, 33124, 33126, 33129, 33157, 33161,
+        33172, 33174, 33177, 33189, 33280, 33282, 33288, 33290, 33301, 33312, 33314, 33320, 33322, 33361, 33364, 33369,
+        33381, 33408, 33410, 33416, 33418, 33429, 33440, 33442, 33448, 33450, 33812, 33817, 33857, 33860, 33873, 33877,
+        33882, 33889, 33892, 33897, 33940, 33945, 34049, 34057, 34066, 34069, 34074, 34086, 34089, 34112, 34113, 34117,
+        34120, 34129, 34132, 34133, 34134, 34137, 34138, 34149, 34150, 34152, 34154, 34177, 34180, 34182, 34185, 34192,
+        34194, 34197, 34200, 34214, 34321, 34326, 34329, 34341, 34369, 34372, 34377, 34378, 34384, 34389, 34393, 34394,
+        34401, 34406, 34410, 34437, 34449, 34458, 34468, 34816, 34818, 34824, 34826, 34837, 34848, 34850, 34856, 34858,
+        34881, 34885, 34897, 34900, 34905, 34917, 34921, 34944, 34946, 34952, 34954, 34965, 34976, 34978, 34984, 34986,
+        35077, 35078, 35089, 35092, 35094, 35109, 35137, 35140, 35142, 35145, 35152, 35154, 35157, 35162, 35169, 35172,
+        35205, 35222, 35225, 35237, 35328, 35330, 35336, 35338, 35349, 35360, 35362, 35368, 35370, 35397, 35409, 35412,
+        35414, 35456, 35458, 35464, 35466, 35477, 35488, 35490, 35496, 35498, 36869, 36881, 36886, 36888, 36889, 36901,
+        36929, 36934, 36937, 36949, 36952, 36954, 36969, 36970, 36997, 37009, 37012, 37014, 37017, 37029, 37121, 37124,
+        37126, 37129, 37136, 37141, 37144, 37146, 37153, 37156, 37158, 37161, 37184, 37189, 37200, 37201, 37204, 37205,
+        37206, 37209, 37218, 37221, 37252, 37254, 37266, 37269, 37272, 37281, 37284, 37286, 37289, 37381, 37393, 37396,
+        37401, 37413, 37444, 37446, 37449, 37456, 37458, 37461, 37464, 37478, 37481, 37509, 37524, 37526, 37545, 37889,
+        37892, 37894, 37904, 37909, 37912, 37926, 37952, 37962, 37969, 37972, 37973, 37974, 37976, 37977, 37984, 37985,
+        37986, 37989, 38020, 38022, 38034, 38036, 38037, 38040, 38049, 38057, 38144, 38149, 38152, 38154, 38160, 38161,
+        38164, 38165, 38166, 38169, 38177, 38181, 38185, 38186, 38209, 38212, 38213, 38214, 38217, 38224, 38225, 38226,
+        38228, 38229, 38230, 38232, 38233, 38234, 38241, 38244, 38245, 38246, 38249, 38273, 38277, 38280, 38289, 38290,
+        38292, 38293, 38294, 38297, 38298, 38304, 38306, 38309, 38312, 38314, 38401, 38404, 38416, 38421, 38425, 38432,
+        38438, 38441, 38469, 38472, 38473, 38481, 38482, 38485, 38486, 38489, 38501, 38504, 38530, 38532, 38537, 38538,
+        38546, 38548, 38549, 38564, 38566, 38569, 38917, 38934, 38937, 38949, 38977, 38982, 38992, 38994, 38997, 38998,
+        39002, 39012, 39013, 39045, 39057, 39062, 39065, 39077, 39172, 39174, 39177, 39184, 39186, 39189, 39192, 39194,
+        39200, 39201, 39204, 39206, 39232, 39234, 39237, 39240, 39242, 39249, 39252, 39253, 39254, 39257, 39266, 39269,
+        39270, 39274, 39297, 39300, 39312, 39314, 39317, 39322, 39329, 39334, 39429, 39445, 39461, 39492, 39494, 39497,
+        39504, 39509, 39512, 39521, 39557, 39569, 39572, 39573, 39574, 40960, 40962, 40968, 40970, 40981, 40992, 40994,
+        41000, 41002, 41029, 41041, 41044, 41046, 41049, 41088, 41090, 41096, 41098, 41109, 41120, 41122, 41128, 41130,
+        41221, 41225, 41233, 41236, 41238, 41241, 41242, 41286, 41289, 41297, 41301, 41304, 41306, 41313, 41316, 41349,
+        41360, 41362, 41366, 41369, 41474, 41480, 41482, 41488, 41497, 41506, 41512, 41514, 41541, 41553, 41558, 41561,
+        41573, 41600, 41602, 41608, 41610, 41621, 41632, 41634, 41640, 41642, 42009, 42021, 42049, 42052, 42064, 42068,
+        42069, 42072, 42074, 42081, 42085, 42086, 42088, 42089, 42117, 42246, 42249, 42256, 42258, 42261, 42264, 42278,
+        42281, 42306, 42309, 42321, 42324, 42325, 42326, 42329, 42341, 42346, 42369, 42372, 42373, 42374, 42377, 42386,
+        42389, 42392, 42501, 42513, 42518, 42522, 42529, 42533, 42564, 42566, 42570, 42578, 42581, 42582, 42584, 42592,
+        42594, 42630, 42640, 42645, 42646, 42649, 42657, 42660, 42662, 43008, 43010, 43016, 43018, 43040, 43042, 43048,
+        43050, 43089, 43092, 43094, 43097, 43136, 43138, 43144, 43146, 43157, 43168, 43170, 43176, 43178, 43269, 43284,
+        43289, 43297, 43301, 43329, 43344, 43349, 43354, 43361, 43366, 43369, 43408, 43414, 43520, 43522, 43528, 43530,
+        43552, 43554, 43560, 43562, 43601, 43604, 43606, 43648, 43650, 43656, 43658, 43669, 43680, 43682, 43688, 43690,
     };
     static const uint16_t kgrid_2bit_1024[1024] = {
             0,     2,     5,     8,    10,    17,    20,    22,    25,    32,    34,    37,    40,    65,    68,    70,
@@ -10918,12 +10199,12 @@ void iq2xs_init_impl(enum ggml_type type) {
     const int nwant = type == GGML_TYPE_IQ1_S ? 3 : type == GGML_TYPE_IQ2_S ? 1 : 2;
     const uint16_t * kgrid = type == GGML_TYPE_IQ2_XXS ? kgrid_2bit_256 :
                              type == GGML_TYPE_IQ2_XS  ? kgrid_2bit_512 :
-                             type == GGML_TYPE_IQ1_S   ? kgrid_1bit_512 : kgrid_2bit_1024;
+                             type == GGML_TYPE_IQ1_S   ? kgrid_1bit_2048 : kgrid_2bit_1024;
     uint64_t * kgrid_q2xs;
     int      * kmap_q2xs;
     uint16_t * kneighbors_q2xs;
 
-    printf("================================================================= %s(grid_size = %d)\n", __func__, grid_size);
+    //printf("================================================================= %s(grid_size = %d)\n", __func__, grid_size);
     uint64_t * the_grid = (uint64_t *)malloc(grid_size*sizeof(uint64_t));
     for (int k = 0; k < grid_size; ++k) {
         int8_t * pos = (int8_t *)(the_grid + k);
@@ -10978,7 +10259,7 @@ void iq2xs_init_impl(enum ggml_type type) {
         }
         num_neighbors += n;
     }
-    printf("%s: %d neighbours in total\n", __func__, num_neighbors);
+    //printf("%s: %d neighbours in total\n", __func__, num_neighbors);
     kneighbors_q2xs = (uint16_t *)malloc((num_neighbors + num_not_in_map)*sizeof(uint16_t));
     iq2_data[gindex].neighbours = kneighbors_q2xs;
     int counter = 0;
@@ -11401,8 +10682,7 @@ static void quantize_row_iq2_xs_impl(const float * restrict x, void * restrict v
     }
 }
 
-size_t quantize_iq2_xxs(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) {
-    (void)hist;
+size_t quantize_iq2_xxs(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) {
     GGML_ASSERT(n_per_row%QK_K == 0);
     int nblock = n_per_row/QK_K;
     char * qrow = (char *)dst;
@@ -11414,8 +10694,7 @@ size_t quantize_iq2_xxs(const float * src, void * dst, int nrow, int n_per_row,
     return nrow * nblock * sizeof(block_iq2_xxs);
 }
 
-size_t quantize_iq2_xs(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) {
-    (void)hist;
+size_t quantize_iq2_xs(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) {
     GGML_ASSERT(n_per_row%QK_K == 0);
     int nblock = n_per_row/QK_K;
     char * qrow = (char *)dst;
@@ -11519,7 +10798,7 @@ void iq3xs_init_impl(int grid_size) {
     int      * kmap_q3xs;
     uint16_t * kneighbors_q3xs;
 
-    printf("================================================================= %s(grid_size = %d)\n", __func__, grid_size);
+    //printf("================================================================= %s(grid_size = %d)\n", __func__, grid_size);
     uint32_t * the_grid = (uint32_t *)malloc(grid_size*sizeof(uint32_t));
     for (int k = 0; k < grid_size; ++k) {
         int8_t * pos = (int8_t *)(the_grid + k);
@@ -11574,7 +10853,7 @@ void iq3xs_init_impl(int grid_size) {
         }
         num_neighbors += n;
     }
-    printf("%s: %d neighbours in total\n", __func__, num_neighbors);
+    //printf("%s: %d neighbours in total\n", __func__, num_neighbors);
     kneighbors_q3xs = (uint16_t *)malloc((num_neighbors + num_not_in_map)*sizeof(uint16_t));
     iq3_data[gindex].neighbours = kneighbors_q3xs;
     int counter = 0;
@@ -11857,8 +11136,7 @@ static void quantize_row_iq3_xxs_impl(int grid_size, const float * restrict x, v
     }
 }
 
-size_t quantize_iq3_xxs(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) {
-    (void)hist;
+size_t quantize_iq3_xxs(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) {
     GGML_ASSERT(n_per_row%QK_K == 0);
     int nblock = n_per_row/QK_K;
     char * qrow = (char *)dst;
@@ -12064,8 +11342,7 @@ static void quantize_row_iq3_s_impl(int block_size, const float * restrict x, vo
 }
 
 #define IQ3S_BLOCK_SIZE 32
-size_t quantize_iq3_s(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) {
-    (void)hist;
+size_t quantize_iq3_s(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) {
     GGML_ASSERT(n_per_row%QK_K == 0);
     int nblock = n_per_row/QK_K;
     float scales[QK_K/IQ3S_BLOCK_SIZE];
@@ -12095,7 +11372,7 @@ void quantize_row_iq3_s(const float * restrict x, void * restrict vy, int k) {
 
 void quantize_row_iq3_s_reference(const float * restrict x, block_iq3_s * restrict y, int k) {
     assert(k % QK_K == 0);
-    quantize_iq3_s(x, y, 1, k, NULL, NULL);
+    quantize_iq3_s(x, y, 1, k, NULL);
 }
 
 
@@ -12161,12 +11438,70 @@ static int iq1_find_best_neighbour(const uint16_t * restrict neighbours, const u
     return grid_index;
 }
 
+static int iq1_find_best_neighbour2(const uint16_t * restrict neighbours, const uint64_t * restrict grid,
+        const float * restrict xval, const float * restrict weight, float scale, int8_t * restrict L, int ngrid) {
+    int num_neighbors = neighbours[0];
+    GGML_ASSERT(num_neighbors > 0);
+    float best_score = FLT_MAX;
+    int grid_index = -1;
+    for (int j = 1; j <= num_neighbors; ++j) {
+        const int8_t * pg = (const int8_t *)(grid + neighbours[j]);
+        float d2 = 0;
+        for (int i = 0; i < 8; ++i) {
+            float q = (pg[i] - 3)/2;
+            float w = weight[i];
+            float diff = scale*q - xval[i];
+            d2 += w*diff*diff;
+        }
+        if (d2 < best_score) {
+            best_score = d2;
+            grid_index = neighbours[j];
+        }
+    }
+    if (grid_index < 0) {
+        for (int i = 0; i < ngrid; ++i) {
+            const int8_t * grid_i = (const int8_t *)(grid + i);
+            float d2 = 0;
+            for (int j = 0; j < 8; ++j) {
+                float w = weight[j];
+                float q = (grid_i[j] - 3)/2;
+                float diff = scale*q - xval[i];
+                d2 += w*diff*diff;
+            }
+            if (d2 < best_score) {
+                best_score = d2;
+                grid_index = i;
+            }
+        }
+    }
+    if (grid_index < 0) {
+        printf("Oops, did not find grid point\n");
+        printf("Have %d neighbours\n", num_neighbors);
+        for (int j = 1; j <= num_neighbors; ++j) {
+            const int8_t * pg = (const int8_t *)(grid + neighbours[j]);
+            float sumqx = 0, sumq2 = 0;
+            for (int i = 0; i < 8; ++i) {
+                float q = (pg[i] - 3)/2;
+                float w = weight[i];
+                sumqx += w*q*xval[i];
+                sumq2 += w*q*q;
+            }
+            printf("    neighbour %d: sumqx = %g sumq2 = %g\n", j, (double)sumqx, (double)sumq2);
+        }
+    }
+    GGML_ASSERT(grid_index >= 0);
+    const int8_t * pg = (const int8_t *)(grid + grid_index);
+    for (int i = 0; i < 8; ++i) L[i] = (pg[i] - 1)/2;
+    return grid_index;
+}
+
 static int iq1_sort_helper(const void * left, const void * right) {
     const float * l = left;
     const float * r = right;
     return *l < *r ? -1 : *l > *r ? 1 : 0;
 }
 
+#define IQ1S_BLOCK_SIZE 32
 static void quantize_row_iq1_s_impl(const float * restrict x, void * restrict vy, int n, const float * restrict quant_weights) {
 
     const int gindex = iq2_data_index(GGML_TYPE_IQ1_S);
@@ -12185,37 +11520,37 @@ static void quantize_row_iq1_s_impl(const float * restrict x, void * restrict vy
 
     block_iq1_s * y = vy;
 
-    float  scales[QK_K/8];
-    float  weight[8];
-    int8_t L[8];
-    float  sumx[9];
-    float  sumw[9];
-    float  pairs[16];
+    float  scales[QK_K/IQ1S_BLOCK_SIZE];
+    float  weight[IQ1S_BLOCK_SIZE];
+    int8_t L[IQ1S_BLOCK_SIZE];
+    float  sumx[IQ1S_BLOCK_SIZE+1];
+    float  sumw[IQ1S_BLOCK_SIZE+1];
+    float  pairs[2*IQ1S_BLOCK_SIZE];
     int * idx = (int *)(pairs + 1);
-    uint8_t hbit[QK_K/8];
+    uint16_t index[IQ1S_BLOCK_SIZE/8];
 
     for (int ibl = 0; ibl < nbl; ++ibl) {
 
         y[ibl].d = GGML_FP32_TO_FP16(0.f);
         memset(y[ibl].qs, 0, QK_K/8);
-        memset(y[ibl].scales, 0, QK_K/16);
+        memset(y[ibl].qh, 0, QK_K/16);
 
         float max_scale = 0;
 
         const float * xbl = x + QK_K*ibl;
         float sumx2 = 0;
         for (int i = 0; i < QK_K; ++i) sumx2 += xbl[i]*xbl[i];
-        float sigma2 = sumx2/QK_K;
+        float sigma2 = 2*sumx2/QK_K;
 
-        for (int ib = 0; ib < QK_K/8; ++ib) {
-            const float * xb = xbl + 8*ib;
-            const float * qw = quant_weights + QK_K*ibl + 8*ib;
-            for (int i = 0; i < 8; ++i) weight[i] = qw[i] * sqrtf(sigma2 + xb[i]*xb[i]);
+        for (int ib = 0; ib < QK_K/IQ1S_BLOCK_SIZE; ++ib) {
+            const float * xb = xbl + IQ1S_BLOCK_SIZE*ib;
+            const float * qw = quant_weights + QK_K*ibl + IQ1S_BLOCK_SIZE*ib;
+            for (int i = 0; i < IQ1S_BLOCK_SIZE; ++i) weight[i] = qw[i] * sqrtf(sigma2 + xb[i]*xb[i]);
             float max = fabsf(xb[0]);
-            for (int i = 1; i < 8; ++i) max = MAX(max, fabsf(xb[i]));
+            for (int i = 1; i < IQ1S_BLOCK_SIZE; ++i) max = MAX(max, fabsf(xb[i]));
             if (!max) {
                 scales[ib] = 0;
-                memset(L, 1, 8);
+                memset(L, 1, IQ1S_BLOCK_SIZE);
                 continue;
             }
             // Here we solve exactly the sum of squared difference (SSD) weighted minimization problem.
@@ -12224,14 +11559,14 @@ static void quantize_row_iq1_s_impl(const float * restrict x, void * restrict vy
             // in ascending order, compute Si = sum[weight[j] xb[j], j = 0...i] and
             // Wi = sum[weight[j], j = 0...i], and use these to quckly get get the optimum scale
             // for each possible and score for each split.
-            for (int j = 0; j < 8; ++j) {
+            for (int j = 0; j < IQ1S_BLOCK_SIZE; ++j) {
                 pairs[2*j] = xb[j];
                 idx[2*j] = j;
             }
-            qsort(pairs, 8, 2*sizeof(float), iq1_sort_helper);
+            qsort(pairs, IQ1S_BLOCK_SIZE, 2*sizeof(float), iq1_sort_helper);
             {
                 sumx[0] = sumw[0] = 0;
-                for (int j = 0; j < 8; ++j) {
+                for (int j = 0; j < IQ1S_BLOCK_SIZE; ++j) {
                     int i = idx[2*j];
                     sumx[j+1] = sumx[j] + weight[i]*xb[i];
                     sumw[j+1] = sumw[j] + weight[i];
@@ -12239,10 +11574,10 @@ static void quantize_row_iq1_s_impl(const float * restrict x, void * restrict vy
             }
             float best_score = 0, scale = max;
             int besti1 = 0, besti2 = 0;
-            for (int i1 = 0; i1 <= 8; ++i1) {
-                for (int i2 = i1; i2 <= 8; ++i2) {
-                    float sumqx = -(sumx[i1] - sumx[0]) + (sumx[8] - sumx[i2]);
-                    float sumq2 =  (sumw[i1] - sumw[0]) + (sumw[8] - sumw[i2]);
+            for (int i1 = 0; i1 <= IQ1S_BLOCK_SIZE; ++i1) {
+                for (int i2 = i1; i2 <= IQ1S_BLOCK_SIZE; ++i2) {
+                    float sumqx = -(sumx[i1] - sumx[0]) + (sumx[IQ1S_BLOCK_SIZE] - sumx[i2]);
+                    float sumq2 =  (sumw[i1] - sumw[0]) + (sumw[IQ1S_BLOCK_SIZE] - sumw[i2]);
                     if (sumq2 > 0 && sumqx*sumqx > best_score*sumq2) {
                         scale = sumqx/sumq2; best_score = scale*sumqx;
                         besti1 = i1; besti2 = i2;
@@ -12251,23 +11586,43 @@ static void quantize_row_iq1_s_impl(const float * restrict x, void * restrict vy
             }
             for (int j =      0; j < besti1; ++j) L[idx[2*j]] = 0;
             for (int j = besti1; j < besti2; ++j) L[idx[2*j]] = 1;
-            for (int j = besti2; j <      8; ++j) L[idx[2*j]] = 2;
+            for (int j = besti2; j < IQ1S_BLOCK_SIZE; ++j) L[idx[2*j]] = 2;
             if (scale < 0) {
-                for (int j = 0; j < 8; ++j) L[j] = 2 - L[j];
+                for (int j = 0; j < IQ1S_BLOCK_SIZE; ++j) L[j] = 2 - L[j];
                 scale = -scale;
             }
-            // Now we check if the solution found above corresponds to a grid point and, if not, use a neighbouring
-            // grid point that minimizes SSD.
-            uint16_t u = 0;
-            for (int j = 0; j < 8; ++j) u |= (L[j] << 2*j);
-            int grid_index = kmap_q2xs[u];
-            if (grid_index < 0) {
-                const uint16_t * neighbours = kneighbors_q2xs - kmap_q2xs[u] - 1;
-                grid_index = iq1_find_best_neighbour(neighbours, kgrid_q2xs, xb, weight, &scale, L, NGRID_IQ2XXS);
-                GGML_ASSERT(grid_index >= 0);
+            bool all_on_grid = true;
+            for (int k = 0; k < IQ1S_BLOCK_SIZE/8; ++k) {
+                uint16_t u = 0;
+                for (int j = 0; j < 8; ++j) u |= (L[8*k+j] << 2*j);
+                int grid_index = kmap_q2xs[u];
+                if (grid_index < 0) {
+                    all_on_grid = false;
+                    const uint16_t * neighbours = kneighbors_q2xs - kmap_q2xs[u] - 1;
+                    grid_index = iq1_find_best_neighbour2(neighbours, kgrid_q2xs, xb + 8*k, weight + 8*k, scale, L + 8*k, NGRID_IQ1S);
+                    GGML_ASSERT(grid_index >= 0);
+                }
+                index[k] = grid_index;
             }
-            y[ibl].qs[ib] = grid_index & 255;
-            hbit[ib] = grid_index >> 8;
+            if (!all_on_grid) {
+                float sumqx = 0, sumq2 = 0;
+                for (int k = 0; k < IQ1S_BLOCK_SIZE/8; ++k) {
+                    const int8_t * pg = (const int8_t *)(kgrid_q2xs + index[k]);
+                    for (int j = 0; j < 8; ++j) {
+                        float w = weight[8*k + j];
+                        float q = (pg[j] - 3)/2;
+                        sumqx += w*q*xb[8*k+j];
+                        sumq2 += w*q*q;
+                    }
+                }
+                if (sumqx > 0 && sumq2 > 0) scale = sumqx/sumq2;
+            }
+            uint16_t h = 0;
+            for (int k = 0; k < IQ1S_BLOCK_SIZE/8; ++k) {
+                y[ibl].qs[(IQ1S_BLOCK_SIZE/8)*ib + k] = index[k] & 255;
+                h |= (index[k] >> 8) << 3*k;
+            }
+            y[ibl].qh[ib] = h;
             GGML_ASSERT(scale >= 0);
             scales[ib] = scale;
             max_scale = MAX(max_scale, scale);
@@ -12278,20 +11633,18 @@ static void quantize_row_iq1_s_impl(const float * restrict x, void * restrict vy
             continue;
         }
 
-        float d = max_scale/15;
-        y[ibl].d = GGML_FP32_TO_FP16(d*1.085f); // 1.085f is another fudge factor. Don't ask me why it is needed.
+        float d = max_scale/31;
+        y[ibl].d = GGML_FP32_TO_FP16(d*1.125f); // 1.085f is another fudge factor. Don't ask me why it is needed.
         float id = 1/d;
-        for (int ib = 0; ib < QK_K/8; ++ib) {
+        for (int ib = 0; ib < QK_K/IQ1S_BLOCK_SIZE; ++ib) {
             int l = nearest_int(0.5f*(id*scales[ib]-1));
-            l = MAX(0, MIN(7, l));
-            if (hbit[ib]) l |= 8;
-            y[ibl].scales[ib/2] |= (l << 4*(ib%2));
+            l = MAX(0, MIN(15, l));
+            y[ibl].qh[ib] |= (l << 12);
         }
     }
 }
 
-size_t quantize_iq1_s(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) {
-    (void)hist;
+size_t quantize_iq1_s(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) {
     GGML_ASSERT(n_per_row%QK_K == 0);
     int nblock = n_per_row/QK_K;
     char * qrow = (char *)dst;
@@ -12316,7 +11669,7 @@ static inline int best_index_int8(int n, const int8_t * val, float x) {
     return x - val[mu-1] < val[mu] - x ? mu-1 : mu;
 }
 
-static void quantize_row_iq4_nl_impl(const int super_block_size, const int block_size, const float * GGML_RESTRICT x,
+static void quantize_row_iq4_nl_impl(const int super_block_size, const int block_size, const float * restrict x,
         ggml_fp16_t * dh, uint8_t * q4, uint16_t * scales_h, uint8_t * scales_l,
         float * scales, float * weight, uint8_t * L,
         const int8_t * values,
@@ -12424,8 +11777,7 @@ static void quantize_row_iq4_nl_impl(const int super_block_size, const int block
     }
 }
 
-size_t quantize_iq4_nl(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) {
-    (void)hist;
+size_t quantize_iq4_nl(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) {
     GGML_ASSERT(n_per_row%QK4_NL == 0);
     int nblock = n_per_row/QK4_NL;
     char * qrow = (char *)dst;
@@ -12455,14 +11807,13 @@ void quantize_row_iq4_nl(const float * restrict x, void * restrict vy, int k) {
 
 void quantize_row_iq4_nl_reference(const float * restrict x, block_iq4_nl * restrict y, int k) {
     assert(k % QK4_NL == 0);
-    quantize_iq4_nl(x, y, 1, k, NULL, NULL);
+    quantize_iq4_nl(x, y, 1, k, NULL);
 }
 
-size_t quantize_iq4_xs(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) {
+size_t quantize_iq4_xs(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) {
 #if QK_K == 64
-    return quantize_iq4_nl(src, dst, nrow, n_per_row, hist, quant_weights);
+    return quantize_iq4_nl(src, dst, nrow, n_per_row, quant_weights);
 #else
-    (void)hist;
     GGML_ASSERT(n_per_row%QK_K == 0);
     int nblock = n_per_row/QK_K;
     char * qrow = (char *)dst;
@@ -12491,7 +11842,7 @@ void quantize_row_iq4_xs(const float * restrict x, void * restrict vy, int k) {
 
 void quantize_row_iq4_xs_reference(const float * restrict x, block_iq4_xs * restrict y, int k) {
     assert(k % QK_K == 0);
-    quantize_iq4_xs(x, y, 1, k, NULL, NULL);
+    quantize_iq4_xs(x, y, 1, k, NULL);
 }
 
 // =============================== 2.5625 bpw
@@ -12664,8 +12015,7 @@ static void quantize_row_iq2_s_impl(const float * restrict x, void * restrict vy
     }
 }
 
-size_t quantize_iq2_s(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) {
-    (void)hist;
+size_t quantize_iq2_s(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) {
     GGML_ASSERT(n_per_row%QK_K == 0);
     int nblock = n_per_row/QK_K;
     char * qrow = (char *)dst;
@@ -12679,7 +12029,7 @@ size_t quantize_iq2_s(const float * src, void * dst, int nrow, int n_per_row, in
 
 void quantize_row_iq2_s_reference(const float * restrict x, block_iq2_s * restrict y, int k) {
     assert(k % QK_K == 0);
-    quantize_iq2_s(x, y, 1, k, NULL, NULL);
+    quantize_iq2_s(x, y, 1, k, NULL);
 }
 
 void quantize_row_iq2_s(const float * restrict x, void * restrict vy, int k) {
diff --git a/ggml-quants.h b/ggml-quants.h
index 316e35687..74aabf415 100644
--- a/ggml-quants.h
+++ b/ggml-quants.h
@@ -1,9 +1,9 @@
 #pragma once
 
-#include "ggml-impl.h"
-
 // GGML internal header
 
+#include "ggml-impl.h"
+
 #include <stdint.h>
 #include <stddef.h>
 
@@ -217,8 +217,8 @@ static_assert(sizeof(block_iq3_s) == sizeof(ggml_fp16_t) + 13*(QK_K/32) + IQ3S_N
 
 typedef struct {
     ggml_fp16_t d;
-    uint8_t qs[QK_K/8];
-    uint8_t scales[QK_K/16];
+    uint8_t  qs[QK_K/8];
+    uint16_t qh[QK_K/32];
 } block_iq1_s;
 static_assert(sizeof(block_iq1_s) == sizeof(ggml_fp16_t) + QK_K/8 + QK_K/16, "wrong iq1_s block size/padding");
 
@@ -261,6 +261,7 @@ void quantize_row_q4_K_reference(const float * GGML_RESTRICT x, block_q4_K * GGM
 void quantize_row_q5_K_reference(const float * GGML_RESTRICT x, block_q5_K * GGML_RESTRICT y, int k);
 void quantize_row_q6_K_reference(const float * GGML_RESTRICT x, block_q6_K * GGML_RESTRICT y, int k);
 void quantize_row_q8_K_reference(const float * GGML_RESTRICT x, block_q8_K * GGML_RESTRICT y, int k);
+
 void quantize_row_iq3_xxs_reference(const float * GGML_RESTRICT x, block_iq3_xxs * GGML_RESTRICT y, int k);
 void quantize_row_iq4_nl_reference (const float * GGML_RESTRICT x, block_iq4_nl  * GGML_RESTRICT y, int k);
 void quantize_row_iq4_xs_reference (const float * GGML_RESTRICT x, block_iq4_xs  * GGML_RESTRICT y, int k);
@@ -280,6 +281,7 @@ void quantize_row_q4_K(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, in
 void quantize_row_q5_K(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int k);
 void quantize_row_q6_K(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int k);
 void quantize_row_q8_K(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int k);
+
 void quantize_row_iq3_xxs(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int k);
 void quantize_row_iq4_nl (const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int k);
 void quantize_row_iq4_xs (const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int k);
@@ -300,6 +302,7 @@ void dequantize_row_q4_K(const block_q4_K * GGML_RESTRICT x, float * GGML_RESTRI
 void dequantize_row_q5_K(const block_q5_K * GGML_RESTRICT x, float * GGML_RESTRICT y, int k);
 void dequantize_row_q6_K(const block_q6_K * GGML_RESTRICT x, float * GGML_RESTRICT y, int k);
 void dequantize_row_q8_K(const block_q8_K * GGML_RESTRICT x, float * GGML_RESTRICT y, int k);
+
 void dequantize_row_iq2_xxs(const block_iq2_xxs * GGML_RESTRICT x, float * GGML_RESTRICT y, int k);
 void dequantize_row_iq2_xs (const block_iq2_xs  * GGML_RESTRICT x, float * GGML_RESTRICT y, int k);
 void dequantize_row_iq2_s  (const block_iq2_s   * GGML_RESTRICT x, float * GGML_RESTRICT y, int k);
@@ -321,6 +324,7 @@ void ggml_vec_dot_q3_K_q8_K(int n, float * GGML_RESTRICT s, size_t bs, const voi
 void ggml_vec_dot_q4_K_q8_K(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
 void ggml_vec_dot_q5_K_q8_K(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
 void ggml_vec_dot_q6_K_q8_K(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
+
 void ggml_vec_dot_iq2_xxs_q8_K(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
 void ggml_vec_dot_iq2_xs_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
 void ggml_vec_dot_iq2_s_q8_K  (int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
@@ -330,26 +334,26 @@ void ggml_vec_dot_iq4_nl_q8_0 (int n, float * GGML_RESTRICT s, size_t bs, const
 void ggml_vec_dot_iq4_xs_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
 void ggml_vec_dot_iq3_s_q8_K  (int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc);
 
-//
 // Quantization utilizing an importance matrix (a.k.a. "Activation aWare Quantization")
-//
-size_t quantize_iq2_xxs(const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix);
-size_t quantize_iq2_xs (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix);
-size_t quantize_iq2_s  (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix);
-size_t quantize_iq3_xxs(const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix);
-size_t quantize_iq1_s  (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix);
-size_t quantize_iq4_nl (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix);
-size_t quantize_iq4_xs (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix);
-size_t quantize_iq3_s  (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix);
-size_t quantize_q2_K   (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix);
-size_t quantize_q3_K   (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix);
-size_t quantize_q4_K   (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix);
-size_t quantize_q5_K   (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix);
-size_t quantize_q6_K   (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix);
-size_t quantize_q4_0   (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix);
-size_t quantize_q4_1   (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix);
-size_t quantize_q5_0   (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix);
-size_t quantize_q5_1   (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix);
+size_t quantize_iq2_xxs(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix);
+size_t quantize_iq2_xs (const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix);
+size_t quantize_iq2_s  (const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix);
+size_t quantize_iq3_xxs(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix);
+size_t quantize_iq1_s  (const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix);
+size_t quantize_iq4_nl (const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix);
+size_t quantize_iq4_xs (const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix);
+size_t quantize_iq3_s  (const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix);
+
+size_t quantize_q2_K(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix);
+size_t quantize_q3_K(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix);
+size_t quantize_q4_K(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix);
+size_t quantize_q5_K(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix);
+size_t quantize_q6_K(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix);
+size_t quantize_q4_0(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix);
+size_t quantize_q4_1(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix);
+size_t quantize_q5_0(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix);
+size_t quantize_q5_1(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix);
+size_t quantize_q8_0(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix);
 
 void iq2xs_init_impl(enum ggml_type type);
 void iq2xs_free_impl(enum ggml_type type);
diff --git a/ggml-sycl.cpp b/ggml-sycl.cpp
index ddd951dd6..6d5684582 100644
--- a/ggml-sycl.cpp
+++ b/ggml-sycl.cpp
@@ -3144,6 +3144,8 @@ namespace dpct
 
 } // COPY from DPCT head files
 
+#define GGML_COMMON_IMPL_SYCL
+#include "ggml-common.h"
 
 static int g_ggml_sycl_debug=0;
 #define GGML_SYCL_DEBUG(...) do{if(g_ggml_sycl_debug) printf(__VA_ARGS__);}while(0)
@@ -3492,6 +3494,31 @@ typedef struct dpct_type_block_iq3_xxs {
 } block_iq3_xxs;
 static_assert(sizeof(block_iq3_xxs) == sizeof(ggml_fp16_t) + 3*(QK_K/8), "wrong iq3_xxs block size/padding");
 
+#define QR3_XS 8
+#define QI3_XS (QK_K / (4*QR3_XS))
+#if QK_K == 64
+#define IQ3S_N_SCALE 2
+#else
+#define IQ3S_N_SCALE QK_K/64
+#endif
+typedef struct {
+    sycl::half d;
+    uint8_t qs[QK_K/4];
+    uint8_t qh[QK_K/32];
+    uint8_t signs[QK_K/8];
+    uint8_t scales[IQ3S_N_SCALE];
+} block_iq3_s;
+static_assert(sizeof(block_iq3_s) == sizeof(ggml_fp16_t) + 13*(QK_K/32) + IQ3S_N_SCALE, "wrong iq3_s block size/padding");
+
+#define QR1_S 8
+#define QI1_S (QK_K / (4*QR1_S))
+typedef struct {
+    sycl::half d;
+    uint8_t qs[QK_K/8];
+    uint8_t scales[QK_K/16];
+} block_iq1_s;
+static_assert(sizeof(block_iq1_s) == sizeof(ggml_fp16_t) + QK_K/8 + QK_K/16, "wrong iq1_s block size/padding");
+
 #define WARP_SIZE 32
 #define MATRIX_ROW_PADDING 512 // last row of quant. matrices is a multiple of this to avoid out-of-bounds memory accesses
 
@@ -4745,388 +4772,6 @@ static void dequantize_block_q6_K(const void * __restrict__ vx, dst_t * __restri
 #endif
 }
 
-static dpct::global_memory<const uint64_t, 1>
-    iq2xxs_grid(sycl::range<1>(256),
-                {
-                    0x0808080808080808, 0x080808080808082b, 0x0808080808081919,
-                    0x0808080808082b08, 0x0808080808082b2b, 0x0808080808190819,
-                    0x0808080808191908, 0x08080808082b0808, 0x08080808082b082b,
-                    0x08080808082b2b08, 0x08080808082b2b2b, 0x0808080819080819,
-                    0x0808080819081908, 0x0808080819190808, 0x0808080819192b08,
-                    0x08080808192b0819, 0x08080808192b1908, 0x080808082b080808,
-                    0x080808082b08082b, 0x080808082b082b2b, 0x080808082b2b082b,
-                    0x0808081908080819, 0x0808081908081908, 0x0808081908190808,
-                    0x0808081908191919, 0x0808081919080808, 0x080808192b081908,
-                    0x080808192b192b08, 0x0808082b08080808, 0x0808082b0808082b,
-                    0x0808082b082b082b, 0x0808082b2b08082b, 0x0808190808080819,
-                    0x0808190808081908, 0x0808190808190808, 0x08081908082b0819,
-                    0x08081908082b1908, 0x0808190819080808, 0x080819081908082b,
-                    0x0808190819082b08, 0x08081908192b0808, 0x080819082b080819,
-                    0x080819082b081908, 0x080819082b190808, 0x080819082b2b1908,
-                    0x0808191908080808, 0x080819190808082b, 0x0808191908082b08,
-                    0x08081919082b0808, 0x080819191908192b, 0x08081919192b2b19,
-                    0x080819192b080808, 0x080819192b190819, 0x0808192b08082b19,
-                    0x0808192b08190808, 0x0808192b19080808, 0x0808192b2b081908,
-                    0x0808192b2b2b1908, 0x08082b0808080808, 0x08082b0808081919,
-                    0x08082b0808082b08, 0x08082b0808191908, 0x08082b08082b2b08,
-                    0x08082b0819080819, 0x08082b0819081908, 0x08082b0819190808,
-                    0x08082b081919082b, 0x08082b082b082b08, 0x08082b1908081908,
-                    0x08082b1919080808, 0x08082b2b0808082b, 0x08082b2b08191908,
-                    0x0819080808080819, 0x0819080808081908, 0x0819080808190808,
-                    0x08190808082b0819, 0x0819080819080808, 0x08190808192b0808,
-                    0x081908082b081908, 0x081908082b190808, 0x081908082b191919,
-                    0x0819081908080808, 0x0819081908082b08, 0x08190819082b0808,
-                    0x0819081919190808, 0x0819081919192b2b, 0x081908192b080808,
-                    0x0819082b082b1908, 0x0819082b19081919, 0x0819190808080808,
-                    0x0819190808082b08, 0x08191908082b0808, 0x08191908082b1919,
-                    0x0819190819082b19, 0x081919082b080808, 0x0819191908192b08,
-                    0x08191919192b082b, 0x0819192b08080808, 0x0819192b0819192b,
-                    0x08192b0808080819, 0x08192b0808081908, 0x08192b0808190808,
-                    0x08192b0819080808, 0x08192b082b080819, 0x08192b1908080808,
-                    0x08192b1908081919, 0x08192b192b2b0808, 0x08192b2b19190819,
-                    0x082b080808080808, 0x082b08080808082b, 0x082b080808082b2b,
-                    0x082b080819081908, 0x082b0808192b0819, 0x082b08082b080808,
-                    0x082b08082b08082b, 0x082b0819082b2b19, 0x082b081919082b08,
-                    0x082b082b08080808, 0x082b082b0808082b, 0x082b190808080819,
-                    0x082b190808081908, 0x082b190808190808, 0x082b190819080808,
-                    0x082b19081919192b, 0x082b191908080808, 0x082b191919080819,
-                    0x082b1919192b1908, 0x082b192b2b190808, 0x082b2b0808082b08,
-                    0x082b2b08082b0808, 0x082b2b082b191908, 0x082b2b2b19081908,
-                    0x1908080808080819, 0x1908080808081908, 0x1908080808190808,
-                    0x1908080808192b08, 0x19080808082b0819, 0x19080808082b1908,
-                    0x1908080819080808, 0x1908080819082b08, 0x190808081919192b,
-                    0x19080808192b0808, 0x190808082b080819, 0x190808082b081908,
-                    0x190808082b190808, 0x1908081908080808, 0x19080819082b0808,
-                    0x19080819192b0819, 0x190808192b080808, 0x190808192b081919,
-                    0x1908082b08080819, 0x1908082b08190808, 0x1908082b19082b08,
-                    0x1908082b1919192b, 0x1908082b192b2b08, 0x1908190808080808,
-                    0x1908190808082b08, 0x19081908082b0808, 0x190819082b080808,
-                    0x190819082b192b19, 0x190819190819082b, 0x19081919082b1908,
-                    0x1908192b08080808, 0x19082b0808080819, 0x19082b0808081908,
-                    0x19082b0808190808, 0x19082b0819080808, 0x19082b0819081919,
-                    0x19082b1908080808, 0x19082b1919192b08, 0x19082b19192b0819,
-                    0x19082b192b08082b, 0x19082b2b19081919, 0x19082b2b2b190808,
-                    0x1919080808080808, 0x1919080808082b08, 0x1919080808190819,
-                    0x1919080808192b19, 0x19190808082b0808, 0x191908082b080808,
-                    0x191908082b082b08, 0x1919081908081908, 0x191908191908082b,
-                    0x191908192b2b1908, 0x1919082b2b190819, 0x191919082b190808,
-                    0x191919082b19082b, 0x1919191908082b2b, 0x1919192b08080819,
-                    0x1919192b19191908, 0x19192b0808080808, 0x19192b0808190819,
-                    0x19192b0808192b19, 0x19192b08192b1908, 0x19192b1919080808,
-                    0x19192b2b08082b08, 0x192b080808081908, 0x192b080808190808,
-                    0x192b080819080808, 0x192b0808192b2b08, 0x192b081908080808,
-                    0x192b081919191919, 0x192b082b08192b08, 0x192b082b192b0808,
-                    0x192b190808080808, 0x192b190808081919, 0x192b191908190808,
-                    0x192b19190819082b, 0x192b19192b081908, 0x192b2b081908082b,
-                    0x2b08080808080808, 0x2b0808080808082b, 0x2b08080808082b2b,
-                    0x2b08080819080819, 0x2b0808082b08082b, 0x2b08081908081908,
-                    0x2b08081908192b08, 0x2b08081919080808, 0x2b08082b08190819,
-                    0x2b08190808080819, 0x2b08190808081908, 0x2b08190808190808,
-                    0x2b08190808191919, 0x2b08190819080808, 0x2b081908192b0808,
-                    0x2b08191908080808, 0x2b0819191908192b, 0x2b0819192b191908,
-                    0x2b08192b08082b19, 0x2b08192b19080808, 0x2b08192b192b0808,
-                    0x2b082b080808082b, 0x2b082b1908081908, 0x2b082b2b08190819,
-                    0x2b19080808081908, 0x2b19080808190808, 0x2b190808082b1908,
-                    0x2b19080819080808, 0x2b1908082b2b0819, 0x2b1908190819192b,
-                    0x2b1908192b080808, 0x2b19082b19081919, 0x2b19190808080808,
-                    0x2b191908082b082b, 0x2b19190819081908, 0x2b19191919190819,
-                    0x2b192b082b080819, 0x2b192b19082b0808, 0x2b2b08080808082b,
-                    0x2b2b080819190808, 0x2b2b08082b081919, 0x2b2b081908082b19,
-                    0x2b2b082b08080808, 0x2b2b190808192b08, 0x2b2b2b0819190808,
-                    0x2b2b2b1908081908,
-                });
-
-static dpct::global_memory<const uint64_t, 1>
-    iq2xs_grid(sycl::range<1>(512),
-               {
-                   0x0808080808080808, 0x080808080808082b, 0x0808080808081919,
-                   0x0808080808082b08, 0x0808080808082b2b, 0x0808080808190819,
-                   0x0808080808191908, 0x080808080819192b, 0x0808080808192b19,
-                   0x08080808082b0808, 0x08080808082b082b, 0x08080808082b1919,
-                   0x08080808082b2b08, 0x0808080819080819, 0x0808080819081908,
-                   0x080808081908192b, 0x0808080819082b19, 0x0808080819190808,
-                   0x080808081919082b, 0x0808080819191919, 0x0808080819192b08,
-                   0x08080808192b0819, 0x08080808192b1908, 0x080808082b080808,
-                   0x080808082b08082b, 0x080808082b081919, 0x080808082b082b08,
-                   0x080808082b190819, 0x080808082b191908, 0x080808082b192b19,
-                   0x080808082b2b0808, 0x0808081908080819, 0x0808081908081908,
-                   0x080808190808192b, 0x0808081908082b19, 0x0808081908190808,
-                   0x080808190819082b, 0x0808081908191919, 0x0808081908192b08,
-                   0x0808081908192b2b, 0x08080819082b0819, 0x08080819082b1908,
-                   0x0808081919080808, 0x080808191908082b, 0x0808081919081919,
-                   0x0808081919082b08, 0x0808081919190819, 0x0808081919191908,
-                   0x08080819192b0808, 0x08080819192b2b08, 0x080808192b080819,
-                   0x080808192b081908, 0x080808192b190808, 0x0808082b08080808,
-                   0x0808082b0808082b, 0x0808082b08081919, 0x0808082b08082b08,
-                   0x0808082b08190819, 0x0808082b08191908, 0x0808082b082b0808,
-                   0x0808082b19080819, 0x0808082b19081908, 0x0808082b19190808,
-                   0x0808082b19191919, 0x0808082b2b080808, 0x0808082b2b082b2b,
-                   0x0808190808080819, 0x0808190808081908, 0x080819080808192b,
-                   0x0808190808082b19, 0x0808190808190808, 0x080819080819082b,
-                   0x0808190808191919, 0x0808190808192b08, 0x08081908082b0819,
-                   0x08081908082b1908, 0x0808190819080808, 0x080819081908082b,
-                   0x0808190819081919, 0x0808190819082b08, 0x0808190819190819,
-                   0x0808190819191908, 0x080819081919192b, 0x08081908192b0808,
-                   0x080819082b080819, 0x080819082b081908, 0x080819082b190808,
-                   0x0808191908080808, 0x080819190808082b, 0x0808191908081919,
-                   0x0808191908082b08, 0x0808191908190819, 0x0808191908191908,
-                   0x08081919082b0808, 0x0808191919080819, 0x0808191919081908,
-                   0x0808191919190808, 0x08081919192b0819, 0x080819192b080808,
-                   0x0808192b08080819, 0x0808192b08081908, 0x0808192b08190808,
-                   0x0808192b082b192b, 0x0808192b19080808, 0x0808192b1908082b,
-                   0x0808192b2b081908, 0x08082b0808080808, 0x08082b080808082b,
-                   0x08082b0808081919, 0x08082b0808082b08, 0x08082b0808082b2b,
-                   0x08082b0808190819, 0x08082b0808191908, 0x08082b08082b0808,
-                   0x08082b08082b1919, 0x08082b0819080819, 0x08082b0819081908,
-                   0x08082b0819190808, 0x08082b0819192b08, 0x08082b082b080808,
-                   0x08082b082b2b0808, 0x08082b082b2b2b2b, 0x08082b1908080819,
-                   0x08082b1908081908, 0x08082b1908190808, 0x08082b1919080808,
-                   0x08082b192b080819, 0x08082b192b082b19, 0x08082b2b08080808,
-                   0x08082b2b082b0808, 0x08082b2b082b2b08, 0x08082b2b2b19192b,
-                   0x08082b2b2b2b0808, 0x0819080808080819, 0x0819080808081908,
-                   0x081908080808192b, 0x0819080808082b19, 0x0819080808190808,
-                   0x081908080819082b, 0x0819080808191919, 0x0819080808192b08,
-                   0x08190808082b0819, 0x08190808082b1908, 0x0819080819080808,
-                   0x081908081908082b, 0x0819080819081919, 0x0819080819082b08,
-                   0x0819080819190819, 0x0819080819191908, 0x08190808192b0808,
-                   0x08190808192b2b2b, 0x081908082b080819, 0x081908082b081908,
-                   0x081908082b190808, 0x0819081908080808, 0x081908190808082b,
-                   0x0819081908081919, 0x0819081908082b08, 0x0819081908190819,
-                   0x0819081908191908, 0x08190819082b0808, 0x0819081919080819,
-                   0x0819081919081908, 0x0819081919190808, 0x081908192b080808,
-                   0x081908192b191908, 0x081908192b19192b, 0x0819082b08080819,
-                   0x0819082b08081908, 0x0819082b0808192b, 0x0819082b08190808,
-                   0x0819082b19080808, 0x0819082b192b0808, 0x0819190808080808,
-                   0x081919080808082b, 0x0819190808081919, 0x0819190808082b08,
-                   0x0819190808190819, 0x0819190808191908, 0x08191908082b0808,
-                   0x0819190819080819, 0x0819190819081908, 0x0819190819082b19,
-                   0x0819190819190808, 0x08191908192b1908, 0x081919082b080808,
-                   0x0819191908080819, 0x0819191908081908, 0x0819191908190808,
-                   0x0819191919080808, 0x0819192b08080808, 0x0819192b08191908,
-                   0x0819192b19082b19, 0x08192b0808080819, 0x08192b0808081908,
-                   0x08192b0808190808, 0x08192b080819082b, 0x08192b0819080808,
-                   0x08192b0819191908, 0x08192b082b08192b, 0x08192b1908080808,
-                   0x08192b1908081919, 0x08192b19192b192b, 0x08192b2b19190819,
-                   0x08192b2b2b2b2b19, 0x082b080808080808, 0x082b08080808082b,
-                   0x082b080808081919, 0x082b080808082b08, 0x082b080808082b2b,
-                   0x082b080808190819, 0x082b080808191908, 0x082b0808082b0808,
-                   0x082b080819080819, 0x082b080819081908, 0x082b080819190808,
-                   0x082b08082b080808, 0x082b08082b2b0808, 0x082b081908080819,
-                   0x082b081908081908, 0x082b081908190808, 0x082b081919080808,
-                   0x082b081919082b08, 0x082b0819192b1919, 0x082b082b08080808,
-                   0x082b082b082b082b, 0x082b082b2b080808, 0x082b082b2b2b2b08,
-                   0x082b190808080819, 0x082b190808081908, 0x082b190808190808,
-                   0x082b1908082b2b19, 0x082b190819080808, 0x082b191908080808,
-                   0x082b191919080819, 0x082b19191919082b, 0x082b19192b192b19,
-                   0x082b192b08080819, 0x082b192b08192b2b, 0x082b192b2b2b192b,
-                   0x082b2b0808080808, 0x082b2b0808082b08, 0x082b2b0808082b2b,
-                   0x082b2b08082b0808, 0x082b2b0819191919, 0x082b2b082b082b08,
-                   0x082b2b082b2b082b, 0x082b2b19192b2b08, 0x082b2b192b190808,
-                   0x082b2b2b08082b08, 0x082b2b2b082b0808, 0x082b2b2b2b08082b,
-                   0x082b2b2b2b082b08, 0x082b2b2b2b082b2b, 0x1908080808080819,
-                   0x1908080808081908, 0x190808080808192b, 0x1908080808082b19,
-                   0x1908080808190808, 0x190808080819082b, 0x1908080808191919,
-                   0x1908080808192b08, 0x19080808082b0819, 0x19080808082b1908,
-                   0x1908080819080808, 0x190808081908082b, 0x1908080819081919,
-                   0x1908080819082b08, 0x1908080819082b2b, 0x1908080819190819,
-                   0x1908080819191908, 0x19080808192b0808, 0x19080808192b1919,
-                   0x190808082b080819, 0x190808082b081908, 0x190808082b190808,
-                   0x1908081908080808, 0x190808190808082b, 0x1908081908081919,
-                   0x1908081908082b08, 0x1908081908190819, 0x1908081908191908,
-                   0x19080819082b0808, 0x1908081919080819, 0x1908081919081908,
-                   0x1908081919190808, 0x190808192b080808, 0x190808192b081919,
-                   0x190808192b2b082b, 0x1908082b08080819, 0x1908082b08081908,
-                   0x1908082b08190808, 0x1908082b0819082b, 0x1908082b082b2b19,
-                   0x1908082b19080808, 0x1908190808080808, 0x190819080808082b,
-                   0x1908190808081919, 0x1908190808082b08, 0x1908190808190819,
-                   0x1908190808191908, 0x1908190808192b19, 0x19081908082b0808,
-                   0x1908190819080819, 0x1908190819081908, 0x1908190819190808,
-                   0x190819082b080808, 0x190819082b191908, 0x1908191908080819,
-                   0x1908191908081908, 0x1908191908190808, 0x19081919082b1908,
-                   0x1908191919080808, 0x190819192b192b2b, 0x1908192b08080808,
-                   0x1908192b08082b2b, 0x1908192b19081908, 0x1908192b19190808,
-                   0x19082b0808080819, 0x19082b0808081908, 0x19082b0808190808,
-                   0x19082b0819080808, 0x19082b0819081919, 0x19082b0819191908,
-                   0x19082b08192b082b, 0x19082b1908080808, 0x19082b1908190819,
-                   0x19082b1919081908, 0x19082b1919190808, 0x19082b19192b2b19,
-                   0x19082b2b08081908, 0x1919080808080808, 0x191908080808082b,
-                   0x1919080808081919, 0x1919080808082b08, 0x1919080808190819,
-                   0x1919080808191908, 0x19190808082b0808, 0x19190808082b2b08,
-                   0x1919080819080819, 0x1919080819081908, 0x1919080819190808,
-                   0x191908082b080808, 0x1919081908080819, 0x1919081908081908,
-                   0x1919081908190808, 0x1919081908191919, 0x1919081919080808,
-                   0x191908191908082b, 0x1919082b08080808, 0x1919082b19081908,
-                   0x1919082b2b2b2b2b, 0x1919190808080819, 0x1919190808081908,
-                   0x1919190808190808, 0x19191908082b0819, 0x1919190819080808,
-                   0x19191908192b0808, 0x191919082b080819, 0x191919082b2b0819,
-                   0x1919191908080808, 0x1919191908082b08, 0x191919192b080808,
-                   0x191919192b082b08, 0x1919192b082b0819, 0x1919192b192b2b08,
-                   0x1919192b2b2b0819, 0x19192b0808080808, 0x19192b0808191908,
-                   0x19192b0819080819, 0x19192b0819190808, 0x19192b082b192b19,
-                   0x19192b1908192b2b, 0x19192b1919080808, 0x19192b191908082b,
-                   0x19192b2b2b081919, 0x192b080808080819, 0x192b080808081908,
-                   0x192b080808190808, 0x192b080819080808, 0x192b080819191908,
-                   0x192b0808192b082b, 0x192b08082b08192b, 0x192b08082b2b2b19,
-                   0x192b081908080808, 0x192b082b082b1908, 0x192b082b19082b2b,
-                   0x192b082b2b19082b, 0x192b190808080808, 0x192b19080819192b,
-                   0x192b191908190808, 0x192b191919080808, 0x192b191919081919,
-                   0x192b19192b2b1908, 0x192b2b0808080819, 0x192b2b08192b2b2b,
-                   0x192b2b19082b1919, 0x192b2b2b0808192b, 0x192b2b2b19191908,
-                   0x192b2b2b192b082b, 0x2b08080808080808, 0x2b0808080808082b,
-                   0x2b08080808081919, 0x2b08080808082b08, 0x2b08080808190819,
-                   0x2b08080808191908, 0x2b080808082b0808, 0x2b080808082b2b2b,
-                   0x2b08080819080819, 0x2b08080819081908, 0x2b08080819190808,
-                   0x2b0808082b080808, 0x2b0808082b08082b, 0x2b0808082b2b2b08,
-                   0x2b0808082b2b2b2b, 0x2b08081908080819, 0x2b08081908081908,
-                   0x2b0808190808192b, 0x2b08081908190808, 0x2b08081919080808,
-                   0x2b08081919190819, 0x2b08081919192b19, 0x2b08082b08080808,
-                   0x2b08082b082b0808, 0x2b08082b2b080808, 0x2b08082b2b08082b,
-                   0x2b08082b2b2b0808, 0x2b08082b2b2b2b08, 0x2b08190808080819,
-                   0x2b08190808081908, 0x2b08190808190808, 0x2b0819080819082b,
-                   0x2b08190808191919, 0x2b08190819080808, 0x2b081908192b0808,
-                   0x2b0819082b082b19, 0x2b08191908080808, 0x2b08191919081908,
-                   0x2b0819192b2b1919, 0x2b08192b08192b08, 0x2b08192b192b2b2b,
-                   0x2b082b0808080808, 0x2b082b0808082b08, 0x2b082b08082b1919,
-                   0x2b082b0819192b2b, 0x2b082b082b080808, 0x2b082b082b08082b,
-                   0x2b082b082b2b2b08, 0x2b082b190808192b, 0x2b082b2b082b082b,
-                   0x2b082b2b2b080808, 0x2b082b2b2b082b08, 0x2b082b2b2b19192b,
-                   0x2b082b2b2b2b2b08, 0x2b19080808080819, 0x2b19080808081908,
-                   0x2b19080808190808, 0x2b19080819080808, 0x2b1908081919192b,
-                   0x2b1908082b081908, 0x2b19081908080808, 0x2b190819082b082b,
-                   0x2b190819192b1908, 0x2b19082b1919192b, 0x2b19082b2b082b19,
-                   0x2b19190808080808, 0x2b19190808081919, 0x2b19190819081908,
-                   0x2b19190819190808, 0x2b19190819192b08, 0x2b191919082b2b19,
-                   0x2b1919192b190808, 0x2b1919192b19082b, 0x2b19192b19080819,
-                   0x2b192b0819190819, 0x2b192b082b2b192b, 0x2b192b1919082b19,
-                   0x2b192b2b08191919, 0x2b192b2b192b0808, 0x2b2b080808080808,
-                   0x2b2b08080808082b, 0x2b2b080808082b08, 0x2b2b080808082b2b,
-                   0x2b2b0808082b0808, 0x2b2b0808082b2b2b, 0x2b2b08082b2b0808,
-                   0x2b2b081919190819, 0x2b2b081919192b19, 0x2b2b08192b2b192b,
-                   0x2b2b082b08080808, 0x2b2b082b0808082b, 0x2b2b082b08082b08,
-                   0x2b2b082b082b2b2b, 0x2b2b082b2b080808, 0x2b2b082b2b2b0808,
-                   0x2b2b190819080808, 0x2b2b19082b191919, 0x2b2b192b192b1919,
-                   0x2b2b192b2b192b08, 0x2b2b2b0808082b2b, 0x2b2b2b08082b0808,
-                   0x2b2b2b08082b082b, 0x2b2b2b08082b2b08, 0x2b2b2b082b2b0808,
-                   0x2b2b2b082b2b2b08, 0x2b2b2b1908081908, 0x2b2b2b192b081908,
-                   0x2b2b2b192b08192b, 0x2b2b2b2b082b2b08, 0x2b2b2b2b082b2b2b,
-                   0x2b2b2b2b2b190819, 0x2b2b2b2b2b2b2b2b,
-               });
-
-static dpct::global_memory<const uint32_t, 1> iq3xxs_grid(
-    sycl::range<1>(256),
-    {
-        0x04040404, 0x04040414, 0x04040424, 0x04040c0c, 0x04040c1c, 0x04040c3e,
-        0x04041404, 0x04041414, 0x04041c0c, 0x04042414, 0x04043e1c, 0x04043e2c,
-        0x040c040c, 0x040c041c, 0x040c0c04, 0x040c0c14, 0x040c140c, 0x040c142c,
-        0x040c1c04, 0x040c1c14, 0x040c240c, 0x040c2c24, 0x040c3e04, 0x04140404,
-        0x04140414, 0x04140424, 0x04140c0c, 0x04141404, 0x04141414, 0x04141c0c,
-        0x04141c1c, 0x04141c3e, 0x04142c0c, 0x04142c3e, 0x04143e2c, 0x041c040c,
-        0x041c043e, 0x041c0c04, 0x041c0c14, 0x041c142c, 0x041c3e04, 0x04240c1c,
-        0x04241c3e, 0x04242424, 0x04242c3e, 0x04243e1c, 0x04243e2c, 0x042c040c,
-        0x042c043e, 0x042c1c14, 0x042c2c14, 0x04341c2c, 0x04343424, 0x043e0c04,
-        0x043e0c24, 0x043e0c34, 0x043e241c, 0x043e340c, 0x0c04040c, 0x0c04041c,
-        0x0c040c04, 0x0c040c14, 0x0c04140c, 0x0c04141c, 0x0c041c04, 0x0c041c14,
-        0x0c041c24, 0x0c04243e, 0x0c042c04, 0x0c0c0404, 0x0c0c0414, 0x0c0c0c0c,
-        0x0c0c1404, 0x0c0c1414, 0x0c14040c, 0x0c14041c, 0x0c140c04, 0x0c140c14,
-        0x0c14140c, 0x0c141c04, 0x0c143e14, 0x0c1c0404, 0x0c1c0414, 0x0c1c1404,
-        0x0c1c1c0c, 0x0c1c2434, 0x0c1c3434, 0x0c24040c, 0x0c24042c, 0x0c242c04,
-        0x0c2c1404, 0x0c2c1424, 0x0c2c2434, 0x0c2c3e0c, 0x0c34042c, 0x0c3e1414,
-        0x0c3e2404, 0x14040404, 0x14040414, 0x14040c0c, 0x14040c1c, 0x14041404,
-        0x14041414, 0x14041434, 0x14041c0c, 0x14042414, 0x140c040c, 0x140c041c,
-        0x140c042c, 0x140c0c04, 0x140c0c14, 0x140c140c, 0x140c1c04, 0x140c341c,
-        0x140c343e, 0x140c3e04, 0x14140404, 0x14140414, 0x14140c0c, 0x14140c3e,
-        0x14141404, 0x14141414, 0x14141c3e, 0x14142404, 0x14142c2c, 0x141c040c,
-        0x141c0c04, 0x141c0c24, 0x141c3e04, 0x141c3e24, 0x14241c2c, 0x14242c1c,
-        0x142c041c, 0x142c143e, 0x142c240c, 0x142c3e24, 0x143e040c, 0x143e041c,
-        0x143e0c34, 0x143e242c, 0x1c04040c, 0x1c040c04, 0x1c040c14, 0x1c04140c,
-        0x1c04141c, 0x1c042c04, 0x1c04342c, 0x1c043e14, 0x1c0c0404, 0x1c0c0414,
-        0x1c0c1404, 0x1c0c1c0c, 0x1c0c2424, 0x1c0c2434, 0x1c14040c, 0x1c14041c,
-        0x1c140c04, 0x1c14142c, 0x1c142c14, 0x1c143e14, 0x1c1c0c0c, 0x1c1c1c1c,
-        0x1c241c04, 0x1c24243e, 0x1c243e14, 0x1c2c0404, 0x1c2c0434, 0x1c2c1414,
-        0x1c2c2c2c, 0x1c340c24, 0x1c341c34, 0x1c34341c, 0x1c3e1c1c, 0x1c3e3404,
-        0x24040424, 0x24040c3e, 0x24041c2c, 0x24041c3e, 0x24042c1c, 0x24042c3e,
-        0x240c3e24, 0x24141404, 0x24141c3e, 0x24142404, 0x24143404, 0x24143434,
-        0x241c043e, 0x241c242c, 0x24240424, 0x24242c0c, 0x24243424, 0x242c142c,
-        0x242c241c, 0x242c3e04, 0x243e042c, 0x243e0c04, 0x243e0c14, 0x243e1c04,
-        0x2c040c14, 0x2c04240c, 0x2c043e04, 0x2c0c0404, 0x2c0c0434, 0x2c0c1434,
-        0x2c0c2c2c, 0x2c140c24, 0x2c141c14, 0x2c143e14, 0x2c1c0414, 0x2c1c2c1c,
-        0x2c240c04, 0x2c24141c, 0x2c24143e, 0x2c243e14, 0x2c2c0414, 0x2c2c1c0c,
-        0x2c342c04, 0x2c3e1424, 0x2c3e2414, 0x34041424, 0x34042424, 0x34042434,
-        0x34043424, 0x340c140c, 0x340c340c, 0x34140c3e, 0x34143424, 0x341c1c04,
-        0x341c1c34, 0x34242424, 0x342c042c, 0x342c2c14, 0x34341c1c, 0x343e041c,
-        0x343e140c, 0x3e04041c, 0x3e04042c, 0x3e04043e, 0x3e040c04, 0x3e041c14,
-        0x3e042c14, 0x3e0c1434, 0x3e0c2404, 0x3e140c14, 0x3e14242c, 0x3e142c14,
-        0x3e1c0404, 0x3e1c0c2c, 0x3e1c1c1c, 0x3e1c3404, 0x3e24140c, 0x3e24240c,
-        0x3e2c0404, 0x3e2c0414, 0x3e2c1424, 0x3e341c04,
-    });
-
-static dpct::global_memory<const uint8_t, 1> ksigns_iq2xs(
-    sycl::range<1>(128),
-    {
-        0,   129, 130, 3,   132, 5,   6,   135, 136, 9,   10,  139, 12,
-        141, 142, 15,  144, 17,  18,  147, 20,  149, 150, 23,  24,  153,
-        154, 27,  156, 29,  30,  159, 160, 33,  34,  163, 36,  165, 166,
-        39,  40,  169, 170, 43,  172, 45,  46,  175, 48,  177, 178, 51,
-        180, 53,  54,  183, 184, 57,  58,  187, 60,  189, 190, 63,  192,
-        65,  66,  195, 68,  197, 198, 71,  72,  201, 202, 75,  204, 77,
-        78,  207, 80,  209, 210, 83,  212, 85,  86,  215, 216, 89,  90,
-        219, 92,  221, 222, 95,  96,  225, 226, 99,  228, 101, 102, 231,
-        232, 105, 106, 235, 108, 237, 238, 111, 240, 113, 114, 243, 116,
-        245, 246, 119, 120, 249, 250, 123, 252, 125, 126, 255,
-    });
-
-static dpct::global_memory<const uint64_t, 1>
-    ksigns64(sycl::range<1>(128),
-             {
-                 0x0000000000000000, 0xff000000000000ff, 0xff0000000000ff00,
-                 0x000000000000ffff, 0xff00000000ff0000, 0x0000000000ff00ff,
-                 0x0000000000ffff00, 0xff00000000ffffff, 0xff000000ff000000,
-                 0x00000000ff0000ff, 0x00000000ff00ff00, 0xff000000ff00ffff,
-                 0x00000000ffff0000, 0xff000000ffff00ff, 0xff000000ffffff00,
-                 0x00000000ffffffff, 0xff0000ff00000000, 0x000000ff000000ff,
-                 0x000000ff0000ff00, 0xff0000ff0000ffff, 0x000000ff00ff0000,
-                 0xff0000ff00ff00ff, 0xff0000ff00ffff00, 0x000000ff00ffffff,
-                 0x000000ffff000000, 0xff0000ffff0000ff, 0xff0000ffff00ff00,
-                 0x000000ffff00ffff, 0xff0000ffffff0000, 0x000000ffffff00ff,
-                 0x000000ffffffff00, 0xff0000ffffffffff, 0xff00ff0000000000,
-                 0x0000ff00000000ff, 0x0000ff000000ff00, 0xff00ff000000ffff,
-                 0x0000ff0000ff0000, 0xff00ff0000ff00ff, 0xff00ff0000ffff00,
-                 0x0000ff0000ffffff, 0x0000ff00ff000000, 0xff00ff00ff0000ff,
-                 0xff00ff00ff00ff00, 0x0000ff00ff00ffff, 0xff00ff00ffff0000,
-                 0x0000ff00ffff00ff, 0x0000ff00ffffff00, 0xff00ff00ffffffff,
-                 0x0000ffff00000000, 0xff00ffff000000ff, 0xff00ffff0000ff00,
-                 0x0000ffff0000ffff, 0xff00ffff00ff0000, 0x0000ffff00ff00ff,
-                 0x0000ffff00ffff00, 0xff00ffff00ffffff, 0xff00ffffff000000,
-                 0x0000ffffff0000ff, 0x0000ffffff00ff00, 0xff00ffffff00ffff,
-                 0x0000ffffffff0000, 0xff00ffffffff00ff, 0xff00ffffffffff00,
-                 0x0000ffffffffffff, 0xffff000000000000, 0x00ff0000000000ff,
-                 0x00ff00000000ff00, 0xffff00000000ffff, 0x00ff000000ff0000,
-                 0xffff000000ff00ff, 0xffff000000ffff00, 0x00ff000000ffffff,
-                 0x00ff0000ff000000, 0xffff0000ff0000ff, 0xffff0000ff00ff00,
-                 0x00ff0000ff00ffff, 0xffff0000ffff0000, 0x00ff0000ffff00ff,
-                 0x00ff0000ffffff00, 0xffff0000ffffffff, 0x00ff00ff00000000,
-                 0xffff00ff000000ff, 0xffff00ff0000ff00, 0x00ff00ff0000ffff,
-                 0xffff00ff00ff0000, 0x00ff00ff00ff00ff, 0x00ff00ff00ffff00,
-                 0xffff00ff00ffffff, 0xffff00ffff000000, 0x00ff00ffff0000ff,
-                 0x00ff00ffff00ff00, 0xffff00ffff00ffff, 0x00ff00ffffff0000,
-                 0xffff00ffffff00ff, 0xffff00ffffffff00, 0x00ff00ffffffffff,
-                 0x00ffff0000000000, 0xffffff00000000ff, 0xffffff000000ff00,
-                 0x00ffff000000ffff, 0xffffff0000ff0000, 0x00ffff0000ff00ff,
-                 0x00ffff0000ffff00, 0xffffff0000ffffff, 0xffffff00ff000000,
-                 0x00ffff00ff0000ff, 0x00ffff00ff00ff00, 0xffffff00ff00ffff,
-                 0x00ffff00ffff0000, 0xffffff00ffff00ff, 0xffffff00ffffff00,
-                 0x00ffff00ffffffff, 0xffffffff00000000, 0x00ffffff000000ff,
-                 0x00ffffff0000ff00, 0xffffffff0000ffff, 0x00ffffff00ff0000,
-                 0xffffffff00ff00ff, 0xffffffff00ffff00, 0x00ffffff00ffffff,
-                 0x00ffffffff000000, 0xffffffffff0000ff, 0xffffffffff00ff00,
-                 0x00ffffffff00ffff, 0xffffffffffff0000, 0x00ffffffffff00ff,
-                 0x00ffffffffffff00, 0xffffffffffffffff,
-             });
-//#endif
-
-static dpct::global_memory<const uint8_t, 1>
-    kmask_iq2xs(sycl::range<1>(8), {1, 2, 4, 8, 16, 32, 64, 128});
-
 template<typename dst_t>
 static void dequantize_block_iq2_xxs(const void * __restrict__ vx, dst_t * __restrict__ yy,
                                      const sycl::nd_item<3> &item_ct1,
@@ -5213,6 +4858,62 @@ static void dequantize_block_iq3_xxs(const void * __restrict__ vx, dst_t * __res
 
 }
 
+template<typename dst_t>
+static void dequantize_block_iq3_s(const void * __restrict__ vx, dst_t * __restrict__ yy,
+                                     const sycl::nd_item<3> &item_ct1,
+                                     const uint32_t *iq3s_grid,
+                                     const uint8_t *ksigns_iq2xs,
+                                     const uint8_t *kmask_iq2xs) {
+
+    const int i = item_ct1.get_group(2);
+    const block_iq3_s * x = (const block_iq3_s  *) vx;
+
+    const int tid = item_ct1.get_local_id(2);
+#if QK_K == 256
+    const int il = tid/8; // 0...3
+    const int ib = tid%8; // 0...7
+    dst_t * y = yy + i*QK_K + 32*ib + 8*il;
+    const uint8_t  * qs = x[i].qs + 8*ib;
+    const uint8_t  * grid1 = (const uint8_t *)(iq3s_grid + qs[2*il+0]);
+    const uint8_t  * grid2 = (const uint8_t *)(iq3s_grid + qs[2*il+1]);
+    const float d = (float)x[i].d * (1 + 2*((x[i].scales[ib/2] >> 4*(ib%2)) & 0xf));
+    const uint8_t signs = x[i].signs[4*ib + il];
+    for (int j = 0; j < 4; ++j) {
+        y[j+0] = d * grid1[j] * (signs & kmask_iq2xs[j+0] ? -1.f : 1.f);
+        y[j+4] = d * grid2[j] * (signs & kmask_iq2xs[j+4] ? -1.f : 1.f);
+    }
+#else
+    assert(false);
+#endif
+
+}
+
+template<typename dst_t>
+static void dequantize_block_iq1_s(const void * __restrict__ vx, dst_t * __restrict__ yy,
+                                     const sycl::nd_item<3> &item_ct1,
+                                     const uint64_t *iq1s_grid,
+                                     const uint8_t *ksigns_iq2xs,
+                                     const uint8_t *kmask_iq2xs) {
+
+    const int i = item_ct1.get_group(2);
+    const block_iq1_s * x = (const block_iq1_s  *) vx;
+
+    const int tid = item_ct1.get_local_id(2);
+#if QK_K == 256
+    const int il = tid/8; // 0...3
+    const int ib = tid%8; // 0...7
+    dst_t * y = yy + i*QK_K + 32*ib + 8*il;
+    const int i8 = 4*ib+il;
+    uint8_t h = x[i].scales[i8/2] >> 4*(i8%2);
+    const int8_t * grid = (const int8_t *)(iq1s_grid + (x[i].qs[i8] | ((h & 8) << 5)));
+    const float d = (float)x[i].d * (2*(h & 7) + 1);
+    for (int j = 0; j < 8; ++j) y[j] = d * grid[j];
+#else
+    assert(false);
+#endif
+
+}
+
 /*
 DPCT1110:4: The total declared local variable size in device function
 dequantize_mul_mat_vec_q2_k exceeds 128 bytes and may cause high register
@@ -8059,6 +7760,76 @@ vec_dot_iq3_xxs_q8_1(const void *__restrict__ vbq,
 #endif
 }
 
+static __dpct_inline__ float
+vec_dot_iq3_s_q8_1(const void *__restrict__ vbq,
+                     const block_q8_1 *__restrict__ bq8_1, const int &iqs,
+                     const uint32_t *iq3s_grid, const uint64_t *ksigns64) {
+#if DPCT_COMPATIBILITY_TEMP >=                                                 \
+    MIN_CC_DP4A // lowest compute capability for integer intrinsics
+#if QK_K == 256
+    const block_iq3_s * bq2 = (const block_iq3_s *) vbq;
+
+    const int ib32 = iqs;
+    const uint8_t  * qs = bq2->qs + 8*ib32;
+    const int8_t   * q8 = bq8_1[ib32].qs;
+    int sumi = 0;
+    for (int l = 0; l < 4; ++l) {
+        const uint32_t * grid1 = iq3s_grid + (qs[2*l+0] | ((bq2->qh[ib32] << (8 - 2*l)) & 256));
+        const uint32_t * grid2 = iq3s_grid + (qs[2*l+1] | ((bq2->qh[ib32] << (7 - 2*l)) & 256));
+        uint32_t signs0 = dpct::vectorized_binary<sycl::uchar4>(
+            ((bq2->signs[4*ib32+l] & 0xf) * 0x01010101) & 0x08040201, 0x08040201, std::equal_to<>());
+        uint32_t signs1 = dpct::vectorized_binary<sycl::uchar4>(
+            ((bq2->signs[4*ib32+l] >>  4) * 0x01010101) & 0x08040201, 0x08040201, std::equal_to<>());
+        const int grid_l = dpct::vectorized_binary<sycl::uchar4>(
+            grid1[0] ^ signs0, signs0, std::minus<>());
+        const int grid_h = dpct::vectorized_binary<sycl::uchar4>(
+            grid2[0] ^ signs1, signs1, std::minus<>());
+        sumi = dpct::dp4a(grid_l, *((int *)q8 + 0), sumi);
+        sumi = dpct::dp4a(grid_h, *((int *)q8 + 1), sumi);
+        q8 += 8;
+    }
+    const float d = (float)bq2->d * (1 + 2*((bq2->scales[ib32/2] >> 4*(ib32%2)) & 0xf)) * bq8_1[ib32].ds[0];
+    return d * sumi;
+#else
+    assert(false);
+    return 0.f;
+#endif
+#else
+    assert(false);
+    return 0.f;
+#endif
+}
+
+static __dpct_inline__ float
+vec_dot_iq1_s_q8_1(const void *__restrict__ vbq,
+                     const block_q8_1 *__restrict__ bq8_1, const int &iqs,
+                     const uint64_t *iq1s_grid, const uint64_t *ksigns64) {
+#if QK_K == 256
+    const block_iq1_s * bq1 = (const block_iq1_s *) vbq;
+
+    const int ib32 = iqs;
+    int sumi1 = 0, sumi2 = 0, sumi3 = 0, sumi4 = 0;
+    const uint8_t h1 = bq1->scales[2*ib32+0];
+    const uint8_t h2 = bq1->scales[2*ib32+1];
+    const int * q8 = (const int *)bq8_1[ib32].qs;
+    const int * grid1 = (const int *)(iq1s_grid + (bq1->qs[4*ib32+0] | ((h1 & 0x08) << 5)));
+    const int * grid2 = (const int *)(iq1s_grid + (bq1->qs[4*ib32+1] | ((h1 & 0x80) << 1)));
+    const int * grid3 = (const int *)(iq1s_grid + (bq1->qs[4*ib32+2] | ((h2 & 0x08) << 5)));
+    const int * grid4 = (const int *)(iq1s_grid + (bq1->qs[4*ib32+3] | ((h2 & 0x80) << 1)));
+    for (int j = 0; j < 2; ++j) {
+        sumi1 = dpct::dp4a(q8[j+0], grid1[j], sumi1);
+        sumi2 = dpct::dp4a(q8[j+2], grid2[j], sumi2);
+        sumi3 = dpct::dp4a(q8[j+4], grid3[j], sumi3);
+        sumi4 = dpct::dp4a(q8[j+6], grid4[j], sumi4);
+    }
+    const float d = (float)bq1->d  * bq8_1[ib32].ds[0];
+    return d * (sumi1 * (2*(h1 & 7) + 1) + sumi2 * (2*((h1 >> 4) & 7) + 1) +
+                sumi3 * (2*(h2 & 7) + 1) + sumi4 * (2*((h2 >> 4) & 7) + 1));
+#else
+    assert(false);
+    return 0.f;
+#endif
+}
 
 template <int qk, int qr, int qi, bool need_sum, typename block_q_t, int mmq_x,
           int mmq_y, int nwarps, load_tiles_sycl_t load_tiles, int vdr,
@@ -8824,6 +8595,98 @@ static void mul_mat_vec_q_iq3_xxs_q8_1(const void * __restrict__ vx, const void
     }
 }
 
+template <int qk, int qi, typename block_q_t, int vdr>
+static void mul_mat_vec_q_iq3_s_q8_1(const void * __restrict__ vx, const void * __restrict__ vy, float * __restrict__ dst, const int ncols, const int nrows,
+                          const sycl::nd_item<3> &item_ct1,
+                          const uint32_t *iq3s_grid_ptr, const uint64_t *ksigns64_ptr ) {
+    const int row = item_ct1.get_group(2) * item_ct1.get_local_range(1) +
+                    item_ct1.get_local_id(1);
+
+    if (row >= nrows) {
+        return;
+    }
+
+    const int blocks_per_row = ncols / qk;
+    const int blocks_per_warp = vdr * WARP_SIZE / qi;
+
+// partial sum for each thread
+    float tmp = 0.0f;
+
+    const block_q_t  * x = (const block_q_t  *) vx;
+    const block_q8_1 * y = (const block_q8_1 *) vy;
+
+    for (int i = item_ct1.get_local_id(2) / (qi / vdr); i < blocks_per_row;
+         i += blocks_per_warp) {
+        const int ibx = row*blocks_per_row + i; // x block index
+
+        const int iby = i * (qk/QK8_1); // y block index that aligns with ibx
+
+        const int iqs =
+            vdr *
+            (item_ct1.get_local_id(2) %
+             (qi / vdr)); // x block quant index when casting the quants to int
+
+        tmp += vec_dot_iq3_s_q8_1(&x[ibx], &y[iby], iqs, iq3s_grid_ptr, ksigns64_ptr);
+    }
+
+    // sum up partial sums and write back result
+#pragma unroll
+    for (int mask = 16; mask > 0; mask >>= 1) {
+        tmp +=
+            dpct::permute_sub_group_by_xor(item_ct1.get_sub_group(), tmp, mask);
+    }
+
+    if (item_ct1.get_local_id(2) == 0) {
+        dst[row] = tmp;
+    }
+}
+
+template <int qk, int qi, typename block_q_t, int vdr>
+static void mul_mat_vec_q_iq1_s_q8_1(const void * __restrict__ vx, const void * __restrict__ vy, float * __restrict__ dst, const int ncols, const int nrows,
+                          const sycl::nd_item<3> &item_ct1,
+                          const uint64_t *iq1s_grid_ptr, const uint64_t *ksigns64_ptr ) {
+    const int row = item_ct1.get_group(2) * item_ct1.get_local_range(1) +
+                    item_ct1.get_local_id(1);
+
+    if (row >= nrows) {
+        return;
+    }
+
+    const int blocks_per_row = ncols / qk;
+    const int blocks_per_warp = vdr * WARP_SIZE / qi;
+
+// partial sum for each thread
+    float tmp = 0.0f;
+
+    const block_q_t  * x = (const block_q_t  *) vx;
+    const block_q8_1 * y = (const block_q8_1 *) vy;
+
+    for (int i = item_ct1.get_local_id(2) / (qi / vdr); i < blocks_per_row;
+         i += blocks_per_warp) {
+        const int ibx = row*blocks_per_row + i; // x block index
+
+        const int iby = i * (qk/QK8_1); // y block index that aligns with ibx
+
+        const int iqs =
+            vdr *
+            (item_ct1.get_local_id(2) %
+             (qi / vdr)); // x block quant index when casting the quants to int
+
+        tmp += vec_dot_iq1_s_q8_1(&x[ibx], &y[iby], iqs, iq1s_grid_ptr, ksigns64_ptr);
+    }
+
+    // sum up partial sums and write back result
+#pragma unroll
+    for (int mask = 16; mask > 0; mask >>= 1) {
+        tmp +=
+            dpct::permute_sub_group_by_xor(item_ct1.get_sub_group(), tmp, mask);
+    }
+
+    if (item_ct1.get_local_id(2) == 0) {
+        dst[row] = tmp;
+    }
+}
+
 template <int qk, int qr, dequantize_kernel_t dequantize_kernel>
 static void dequantize_mul_mat_vec(const void * __restrict__ vx, const dfloat * __restrict__ y, float * __restrict__ dst, const int ncols, const int nrows,
                                    const sycl::nd_item<3> &item_ct1) {
@@ -10509,6 +10372,64 @@ static void dequantize_row_iq3_xxs_sycl(const void *vx, dst_t *y, const int k,
     }
 }
 
+template <typename dst_t>
+static void dequantize_row_iq3_s_sycl(const void *vx, dst_t *y, const int k,
+                                        dpct::queue_ptr stream) {
+    const int nb = k / QK_K;
+    {
+        iq3s_grid.init(*stream);
+        ksigns_iq2xs.init(*stream);
+        kmask_iq2xs.init(*stream);
+
+        dpct::has_capability_or_fail(stream->get_device(),
+                                     {sycl::aspect::fp16});
+
+        stream->submit([&](sycl::handler &cgh) {
+            auto iq3s_grid_ptr_ct1 = iq3s_grid.get_ptr();
+            auto ksigns_iq2xs_ptr_ct1 = ksigns_iq2xs.get_ptr();
+            auto kmask_iq2xs_ptr_ct1 = kmask_iq2xs.get_ptr();
+
+            cgh.parallel_for(sycl::nd_range<3>(sycl::range<3>(1, 1, nb) *
+                                                   sycl::range<3>(1, 1, 32),
+                                               sycl::range<3>(1, 1, 32)),
+                             [=](sycl::nd_item<3> item_ct1) {
+                                 dequantize_block_iq3_s(
+                                     vx, y, item_ct1, iq3s_grid_ptr_ct1,
+                                     ksigns_iq2xs_ptr_ct1, kmask_iq2xs_ptr_ct1);
+                             });
+        });
+    }
+}
+
+template <typename dst_t>
+static void dequantize_row_iq1_s_sycl(const void *vx, dst_t *y, const int k,
+                                        dpct::queue_ptr stream) {
+    const int nb = k / QK_K;
+    {
+        iq1s_grid.init(*stream);
+        ksigns_iq2xs.init(*stream);
+        kmask_iq2xs.init(*stream);
+
+        dpct::has_capability_or_fail(stream->get_device(),
+                                     {sycl::aspect::fp16});
+
+        stream->submit([&](sycl::handler &cgh) {
+            auto iq1s_grid_ptr_ct1 = iq1s_grid.get_ptr();
+            auto ksigns_iq2xs_ptr_ct1 = ksigns_iq2xs.get_ptr();
+            auto kmask_iq2xs_ptr_ct1 = kmask_iq2xs.get_ptr();
+
+            cgh.parallel_for(sycl::nd_range<3>(sycl::range<3>(1, 1, nb) *
+                                                   sycl::range<3>(1, 1, 32),
+                                               sycl::range<3>(1, 1, 32)),
+                             [=](sycl::nd_item<3> item_ct1) {
+                                 dequantize_block_iq1_s(
+                                     vx, y, item_ct1, iq1s_grid_ptr_ct1,
+                                     ksigns_iq2xs_ptr_ct1, kmask_iq2xs_ptr_ct1);
+                             });
+        });
+    }
+}
+
 template <typename src_t, typename dst_t>
 static void convert_unary_sycl(const void *__restrict__ vx,
                                dst_t *__restrict__ y, const int k,
@@ -10559,6 +10480,10 @@ static to_fp16_sycl_t ggml_get_to_fp16_sycl(ggml_type type) try {
             return dequantize_row_iq2_xs_sycl;
         case GGML_TYPE_IQ3_XXS:
             return dequantize_row_iq3_xxs_sycl;
+        case GGML_TYPE_IQ3_S:
+            return dequantize_row_iq3_s_sycl;
+        case GGML_TYPE_IQ1_S:
+            return dequantize_row_iq1_s_sycl;
         case GGML_TYPE_F32:
             return convert_unary_sycl<float>;
         default:
@@ -10599,6 +10524,10 @@ static to_fp32_sycl_t ggml_get_to_fp32_sycl(ggml_type type) {
             return dequantize_row_iq2_xs_sycl;
         case GGML_TYPE_IQ3_XXS:
             return dequantize_row_iq3_xxs_sycl;
+        case GGML_TYPE_IQ3_S:
+            return dequantize_row_iq3_s_sycl;
+        case GGML_TYPE_IQ1_S:
+            return dequantize_row_iq1_s_sycl;
         case GGML_TYPE_F16:
             return convert_unary_sycl<sycl::half>;
         default:
@@ -11188,6 +11117,61 @@ static void mul_mat_vec_iq3_xxs_q8_1_sycl(const void *vx, const void *vy,
     }
 }
 
+static void mul_mat_vec_iq3_s_q8_1_sycl(const void *vx, const void *vy,
+                                          float *dst, const int ncols,
+                                          const int nrows,
+                                          dpct::queue_ptr stream) {
+    GGML_ASSERT(ncols % QK_K == 0);
+    const int block_num_y = (nrows + GGML_SYCL_MMV_Y - 1) / GGML_SYCL_MMV_Y;
+    const sycl::range<3> block_nums(1, 1, block_num_y);
+    const sycl::range<3> block_dims(1, GGML_SYCL_MMV_Y, WARP_SIZE);
+    {
+        iq3s_grid.init(*stream);
+        ksigns64.init(*stream);
+
+        stream->submit([&](sycl::handler &cgh) {
+            auto iq3s_grid_ptr_ct1 = iq3s_grid.get_ptr();
+            auto ksigns64_ptr_ct1 = ksigns64.get_ptr();
+
+            cgh.parallel_for(
+                sycl::nd_range<3>(block_nums * block_dims, block_dims),
+                [=](sycl::nd_item<3> item_ct1)
+                    [[intel::reqd_sub_group_size(32)]] {
+                        mul_mat_vec_q_iq3_s_q8_1<QK_K, QI3_XS, block_iq3_s, 1>(
+                            vx, vy, dst, ncols, nrows, item_ct1,
+                            iq3s_grid_ptr_ct1, ksigns64_ptr_ct1);
+                    });
+        });
+    }
+}
+
+static void mul_mat_vec_iq1_s_q8_1_sycl(const void *vx, const void *vy,
+                                          float *dst, const int ncols,
+                                          const int nrows,
+                                          dpct::queue_ptr stream) {
+    GGML_ASSERT(ncols % QK_K == 0);
+    const int block_num_y = (nrows + GGML_SYCL_MMV_Y - 1) / GGML_SYCL_MMV_Y;
+    const sycl::range<3> block_nums(1, 1, block_num_y);
+    const sycl::range<3> block_dims(1, GGML_SYCL_MMV_Y, WARP_SIZE);
+    {
+        iq1s_grid.init(*stream);
+        ksigns64.init(*stream);
+
+        stream->submit([&](sycl::handler &cgh) {
+            auto iq1s_grid_ptr_ct1 = iq1s_grid.get_ptr();
+            auto ksigns64_ptr_ct1 = ksigns64.get_ptr();
+
+            cgh.parallel_for(
+                sycl::nd_range<3>(block_nums * block_dims, block_dims),
+                [=](sycl::nd_item<3> item_ct1)
+                    [[intel::reqd_sub_group_size(32)]] {
+                        mul_mat_vec_q_iq1_s_q8_1<QK_K, QI1_S, block_iq1_s, 1>(
+                            vx, vy, dst, ncols, nrows, item_ct1,
+                            iq1s_grid_ptr_ct1, ksigns64_ptr_ct1);
+                    });
+        });
+    }
+}
 
 static void ggml_mul_mat_q4_0_q8_1_sycl(const void *vx, const void *vy,
                                         float *dst, const int ncols_x,
@@ -13936,8 +13920,11 @@ static int64_t get_row_rounding(ggml_type type, const std::array<float, GGML_SYC
         case GGML_TYPE_Q5_K:
         case GGML_TYPE_IQ2_XXS:
         case GGML_TYPE_IQ2_XS:
+        case GGML_TYPE_IQ1_S:
         case GGML_TYPE_IQ3_XXS:
             return max_compute_capability >= VER_GEN9 ? 128 : 64;
+        case GGML_TYPE_IQ3_S:
+            return max_compute_capability >= VER_GEN9 ? 128 : 64;
         case GGML_TYPE_Q6_K:
             return 64;
         default:
@@ -13998,6 +13985,12 @@ inline void ggml_sycl_op_mul_mat_vec_q(
         case GGML_TYPE_IQ3_XXS:
             mul_mat_vec_iq3_xxs_q8_1_sycl(src0_dd_i, src1_ddq_i, dst_dd_i, ne00, row_diff, stream);
             break;
+        case GGML_TYPE_IQ3_S:
+            mul_mat_vec_iq3_s_q8_1_sycl(src0_dd_i, src1_ddq_i, dst_dd_i, ne00, row_diff, stream);
+            break;
+        case GGML_TYPE_IQ1_S:
+            mul_mat_vec_iq1_s_q8_1_sycl(src0_dd_i, src1_ddq_i, dst_dd_i, ne00, row_diff, stream);
+            break;
         default:
             GGML_ASSERT(false);
             break;
@@ -17343,9 +17336,8 @@ GGML_CALL static bool ggml_backend_sycl_supports_op(ggml_backend_t backend, cons
                     return false;
                 }
                 ggml_type a_type = a->type;
-                if (a_type == GGML_TYPE_IQ2_XXS || a_type == GGML_TYPE_IQ2_XS || a_type == GGML_TYPE_IQ3_XXS ||
-                    a_type == GGML_TYPE_IQ1_S   || a_type == GGML_TYPE_IQ4_NL || a_type == GGML_TYPE_IQ3_S   ||
-                    a_type == GGML_TYPE_IQ2_S   || a_type == GGML_TYPE_IQ4_XS) {
+                if (a_type == GGML_TYPE_IQ4_NL || a_type == GGML_TYPE_IQ2_S ||
+                    a_type == GGML_TYPE_IQ4_XS) {
                     return false;
                 }
                 return true;
diff --git a/ggml-vulkan.cpp b/ggml-vulkan.cpp
index 5a1b3f477..d41aa7d22 100644
--- a/ggml-vulkan.cpp
+++ b/ggml-vulkan.cpp
@@ -4102,45 +4102,7 @@ static void ggml_vk_test_transfer(ggml_backend_vk_context * ctx, size_t ne, bool
 }
 
 static void ggml_vk_quantize_data(const float * from, void * to, size_t ne, ggml_type quant) {
-    std::vector<int64_t> hist_cur(1 << 4, 0);
-
-    switch(quant) {
-    case GGML_TYPE_F32:
-        memcpy(to, from, sizeof(float) * ne);
-        break;
-    case GGML_TYPE_Q4_0:
-        ggml_quantize_q4_0(from, to, ne, ne, hist_cur.data());
-        break;
-    case GGML_TYPE_Q4_1:
-        ggml_quantize_q4_1(from, to, ne, ne, hist_cur.data());
-        break;
-    case GGML_TYPE_Q5_0:
-        ggml_quantize_q5_0(from, to, ne, ne, hist_cur.data());
-        break;
-    case GGML_TYPE_Q5_1:
-        ggml_quantize_q5_1(from, to, ne, ne, hist_cur.data());
-        break;
-    case GGML_TYPE_Q8_0:
-        ggml_quantize_q8_0(from, to, ne, ne, hist_cur.data());
-        break;
-    case GGML_TYPE_Q2_K:
-        ggml_quantize_q2_K(from, to, ne, ne, hist_cur.data());
-        break;
-    case GGML_TYPE_Q3_K:
-        ggml_quantize_q3_K(from, to, ne, ne, hist_cur.data());
-        break;
-    case GGML_TYPE_Q4_K:
-        ggml_quantize_q4_K(from, to, ne, ne, hist_cur.data());
-        break;
-    case GGML_TYPE_Q5_K:
-        ggml_quantize_q5_K(from, to, ne, ne, hist_cur.data());
-        break;
-    case GGML_TYPE_Q6_K:
-        ggml_quantize_q6_K(from, to, ne, ne, hist_cur.data());
-        break;
-    default:
-        GGML_ASSERT(false);
-    }
+    ggml_quantize_chunk(quant, from, to, 0, 1, ne, nullptr);
 }
 
 static void ggml_vk_test_dequant(ggml_backend_vk_context * ctx, size_t ne, ggml_type quant) {
diff --git a/ggml.c b/ggml.c
index 123ccf335..8103e8679 100644
--- a/ggml.c
+++ b/ggml.c
@@ -857,7 +857,7 @@ inline static float vaddvq_f32(float32x4_t v) {
     #define GGML_F16x8              float16x8_t
     #define GGML_F16x8_ZERO         vdupq_n_f16(0.0f)
     #define GGML_F16x8_SET1(x)      vdupq_n_f16(x)
-    #define GGML_F16x8_LOAD(x)      vld1q_f16((const __fp16 *)(x))
+    #define GGML_F16x8_LOAD(x)      vld1q_f16((const ggml_fp16_internal_t *)(x))
     #define GGML_F16x8_STORE        vst1q_f16
     #define GGML_F16x8_FMA(a, b, c) vfmaq_f16(a, b, c)
     #define GGML_F16x8_ADD          vaddq_f16
@@ -900,7 +900,7 @@ inline static float vaddvq_f32(float32x4_t v) {
     #define GGML_F32Cx4              float32x4_t
     #define GGML_F32Cx4_ZERO         vdupq_n_f32(0.0f)
     #define GGML_F32Cx4_SET1(x)      vdupq_n_f32(x)
-    #define GGML_F32Cx4_LOAD(x)      vcvt_f32_f16(vld1_f16((const __fp16 *)(x)))
+    #define GGML_F32Cx4_LOAD(x)      vcvt_f32_f16(vld1_f16((const ggml_fp16_internal_t *)(x)))
     #define GGML_F32Cx4_STORE(x, y)  vst1_f16(x, vcvt_f16_f32(y))
     #define GGML_F32Cx4_FMA(a, b, c) vfmaq_f32(a, b, c)
     #define GGML_F32Cx4_ADD          vaddq_f32
@@ -20160,133 +20160,6 @@ void ggml_quantize_free(void) {
     ggml_critical_section_end();
 }
 
-size_t ggml_quantize_q4_0(const float * src, void * dst, int n, int k, int64_t * hist) {
-    assert(k % QK4_0 == 0);
-    const int nb = k / QK4_0;
-
-    for (int b = 0; b < n; b += k) {
-        block_q4_0 * restrict y = (block_q4_0 *) dst + b/QK4_0;
-
-        quantize_row_q4_0_reference(src + b, y, k);
-
-        for (int i = 0; i < nb; i++) {
-            for (int j = 0; j < QK4_0; j += 2) {
-                const uint8_t vi0 = y[i].qs[j/2] & 0x0F;
-                const uint8_t vi1 = y[i].qs[j/2] >> 4;
-
-                hist[vi0]++;
-                hist[vi1]++;
-            }
-        }
-    }
-
-    return (n/QK4_0*sizeof(block_q4_0));
-}
-
-size_t ggml_quantize_q4_1(const float * src, void * dst, int n, int k, int64_t * hist) {
-    assert(k % QK4_1 == 0);
-    const int nb = k / QK4_1;
-
-    for (int b = 0; b < n; b += k) {
-        block_q4_1 * restrict y = (block_q4_1 *) dst + b/QK4_1;
-
-        quantize_row_q4_1_reference(src + b, y, k);
-
-        for (int i = 0; i < nb; i++) {
-            for (int j = 0; j < QK4_1; j += 2) {
-                const uint8_t vi0 = y[i].qs[j/2] & 0x0F;
-                const uint8_t vi1 = y[i].qs[j/2] >> 4;
-
-                hist[vi0]++;
-                hist[vi1]++;
-            }
-        }
-    }
-
-    return (n/QK4_1*sizeof(block_q4_1));
-}
-
-size_t ggml_quantize_q5_0(const float * src, void * dst, int n, int k, int64_t * hist) {
-    assert(k % QK5_0 == 0);
-    const int nb = k / QK5_0;
-
-    for (int b = 0; b < n; b += k) {
-        block_q5_0 * restrict y = (block_q5_0 *)dst + b/QK5_0;
-
-        quantize_row_q5_0_reference(src + b, y, k);
-
-        for (int i = 0; i < nb; i++) {
-            uint32_t qh;
-            memcpy(&qh, &y[i].qh, sizeof(qh));
-
-            for (int j = 0; j < QK5_0; j += 2) {
-                const uint8_t vh0 = ((qh & (1u << (j/2 + 0 ))) >> (j/2 + 0 )) << 4;
-                const uint8_t vh1 = ((qh & (1u << (j/2 + 16))) >> (j/2 + 12));
-
-                // cast to 16 bins
-                const uint8_t vi0 = ((y[i].qs[j/2] & 0x0F) | vh0) / 2;
-                const uint8_t vi1 = ((y[i].qs[j/2] >>   4) | vh1) / 2;
-
-                hist[vi0]++;
-                hist[vi1]++;
-            }
-        }
-    }
-
-    return (n/QK5_0*sizeof(block_q5_0));
-}
-
-size_t ggml_quantize_q5_1(const float * src, void * dst, int n, int k, int64_t * hist) {
-    assert(k % QK5_1 == 0);
-    const int nb = k / QK5_1;
-
-    for (int b = 0; b < n; b += k) {
-        block_q5_1 * restrict y = (block_q5_1 *)dst + b/QK5_1;
-
-        quantize_row_q5_1_reference(src + b, y, k);
-
-        for (int i = 0; i < nb; i++) {
-            uint32_t qh;
-            memcpy(&qh, &y[i].qh, sizeof(qh));
-
-            for (int j = 0; j < QK5_1; j += 2) {
-                const uint8_t vh0 = ((qh & (1u << (j/2 + 0 ))) >> (j/2 + 0 )) << 4;
-                const uint8_t vh1 = ((qh & (1u << (j/2 + 16))) >> (j/2 + 12));
-
-                // cast to 16 bins
-                const uint8_t vi0 = ((y[i].qs[j/2] & 0x0F) | vh0) / 2;
-                const uint8_t vi1 = ((y[i].qs[j/2] >>   4) | vh1) / 2;
-
-                hist[vi0]++;
-                hist[vi1]++;
-            }
-        }
-    }
-
-    return (n/QK5_1*sizeof(block_q5_1));
-}
-
-size_t ggml_quantize_q8_0(const float * src, void * dst, int n, int k, int64_t * hist) {
-    assert(k % QK8_0 == 0);
-    const int nb = k / QK8_0;
-
-    for (int b = 0; b < n; b += k) {
-        block_q8_0 * restrict y = (block_q8_0 *)dst + b/QK8_0;
-
-        quantize_row_q8_0_reference(src + b, y, k);
-
-        for (int i = 0; i < nb; i++) {
-            for (int j = 0; j < QK8_0; ++j) {
-                const int8_t vi = y[i].qs[j];
-
-                hist[vi/16 + 8]++;
-            }
-        }
-    }
-
-    return (n/QK8_0*sizeof(block_q8_0));
-}
-
 bool ggml_quantize_requires_imatrix(enum ggml_type type) {
     return
         type == GGML_TYPE_IQ2_XXS ||
@@ -20294,177 +20167,52 @@ bool ggml_quantize_requires_imatrix(enum ggml_type type) {
         type == GGML_TYPE_IQ1_S;
 }
 
-size_t ggml_quantize_chunk(enum ggml_type type, const float * src, void * dst, int start,
-        int nrows, int n_per_row, int64_t * hist, const float * imatrix) {
+size_t ggml_quantize_chunk(
+        enum ggml_type   type,
+           const float * src,
+                  void * dst,
+                   int   start,
+                   int   nrows,
+                   int   n_per_row,
+           const float * imatrix) {
+    const int n = nrows * n_per_row;
+
+    if (ggml_quantize_requires_imatrix(type)) {
+        GGML_ASSERT(imatrix != NULL);
+    }
+
+    GGML_ASSERT(start % type_traits[type].blck_size == 0);
+    GGML_ASSERT(start % n_per_row == 0);
+
     ggml_quantize_init(type); // this is noop if already initialized
+
+    const size_t start_row = start / n_per_row;
+    const size_t row_size  = ggml_row_size(type, n_per_row);
+
     size_t result = 0;
-    int n = nrows * n_per_row;
+
     switch (type) {
-        case GGML_TYPE_Q4_0:
-            {
-                GGML_ASSERT(start % QK4_0 == 0);
-                GGML_ASSERT(start % n_per_row == 0);
-                size_t start_row = start / n_per_row;
-                size_t row_size = ggml_row_size(type, n_per_row);
-                result = quantize_q4_0(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix);
-                GGML_ASSERT(result == row_size * nrows);
-            } break;
-        case GGML_TYPE_Q4_1:
-            {
-                GGML_ASSERT(start % QK4_1 == 0);
-                GGML_ASSERT(start % n_per_row == 0);
-                size_t start_row = start / n_per_row;
-                size_t row_size = ggml_row_size(type, n_per_row);
-                result = quantize_q4_1(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix);
-                GGML_ASSERT(result == row_size * nrows);
-            } break;
-        case GGML_TYPE_Q5_0:
-            {
-                GGML_ASSERT(start % QK5_0 == 0);
-                GGML_ASSERT(start % n_per_row == 0);
-                size_t start_row = start / n_per_row;
-                size_t row_size = ggml_row_size(type, n_per_row);
-                result = quantize_q5_0(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix);
-                GGML_ASSERT(result == row_size * nrows);
-            } break;
-        case GGML_TYPE_Q5_1:
-            {
-                GGML_ASSERT(start % QK5_1 == 0);
-                GGML_ASSERT(start % n_per_row == 0);
-                size_t start_row = start / n_per_row;
-                size_t row_size = ggml_row_size(type, n_per_row);
-                result = quantize_q5_1(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix);
-                GGML_ASSERT(result == row_size * nrows);
-            } break;
-        case GGML_TYPE_Q8_0:
-            {
-                GGML_ASSERT(start % QK8_0 == 0);
-                block_q8_0 * block = (block_q8_0*)dst + start / QK8_0;
-                result = ggml_quantize_q8_0(src + start, block, n, n, hist);
-            } break;
-        case GGML_TYPE_Q2_K:
-            {
-                GGML_ASSERT(start % QK_K == 0);
-                GGML_ASSERT(start % n_per_row == 0);
-                size_t start_row = start / n_per_row;
-                size_t row_size = ggml_row_size(type, n_per_row);
-                result = quantize_q2_K(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix);
-                GGML_ASSERT(result == row_size * nrows);
-            } break;
-        case GGML_TYPE_Q3_K:
-            {
-                GGML_ASSERT(start % QK_K == 0);
-                GGML_ASSERT(start % n_per_row == 0);
-                size_t start_row = start / n_per_row;
-                size_t row_size = ggml_row_size(type, n_per_row);
-                result = quantize_q3_K(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix);
-                GGML_ASSERT(result == row_size * nrows);
-            } break;
-        case GGML_TYPE_Q4_K:
-            {
-                GGML_ASSERT(start % QK_K == 0);
-                GGML_ASSERT(start % n_per_row == 0);
-                size_t start_row = start / n_per_row;
-                size_t row_size = ggml_row_size(type, n_per_row);
-                result = quantize_q4_K(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix);
-                GGML_ASSERT(result == row_size * nrows);
-            } break;
-        case GGML_TYPE_Q5_K:
-            {
-                GGML_ASSERT(start % QK_K == 0);
-                GGML_ASSERT(start % n_per_row == 0);
-                size_t start_row = start / n_per_row;
-                size_t row_size = ggml_row_size(type, n_per_row);
-                result = quantize_q5_K(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix);
-                GGML_ASSERT(result == row_size * nrows);
-            } break;
-        case GGML_TYPE_Q6_K:
-            {
-                GGML_ASSERT(start % QK_K == 0);
-                GGML_ASSERT(start % n_per_row == 0);
-                size_t start_row = start / n_per_row;
-                size_t row_size = ggml_row_size(type, n_per_row);
-                result = quantize_q6_K(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix);
-                GGML_ASSERT(result == row_size * nrows);
-            } break;
-        case GGML_TYPE_IQ2_XXS:
-            {
-                GGML_ASSERT(start % QK_K == 0);
-                GGML_ASSERT(start % n_per_row == 0);
-                GGML_ASSERT(imatrix);
-                size_t start_row = start / n_per_row;
-                size_t row_size = ggml_row_size(type, n_per_row);
-                result = quantize_iq2_xxs(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix);
-                GGML_ASSERT(result == row_size * nrows);
-            } break;
-        case GGML_TYPE_IQ2_XS:
-            {
-                GGML_ASSERT(start % QK_K == 0);
-                GGML_ASSERT(start % n_per_row == 0);
-                GGML_ASSERT(imatrix);
-                size_t start_row = start / n_per_row;
-                size_t row_size = ggml_row_size(type, n_per_row);
-                result = quantize_iq2_xs(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix);
-                GGML_ASSERT(result == row_size * nrows);
-            } break;
-        case GGML_TYPE_IQ3_XXS:
-            {
-                GGML_ASSERT(start % QK_K == 0);
-                GGML_ASSERT(start % n_per_row == 0);
-                size_t start_row = start / n_per_row;
-                size_t row_size = ggml_row_size(type, n_per_row);
-                result = quantize_iq3_xxs(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix);
-                GGML_ASSERT(result == row_size * nrows);
-            } break;
-        case GGML_TYPE_IQ3_S:
-            {
-                GGML_ASSERT(start % QK_K == 0);
-                GGML_ASSERT(start % n_per_row == 0);
-                size_t start_row = start / n_per_row;
-                size_t row_size = ggml_row_size(type, n_per_row);
-                result = quantize_iq3_s(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix);
-                GGML_ASSERT(result == row_size * nrows);
-            } break;
-        case GGML_TYPE_IQ2_S:
-            {
-                GGML_ASSERT(start % QK_K == 0);
-                GGML_ASSERT(start % n_per_row == 0);
-                size_t start_row = start / n_per_row;
-                size_t row_size = ggml_row_size(type, n_per_row);
-                result = quantize_iq2_s(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix);
-                GGML_ASSERT(result == row_size * nrows);
-            } break;
-        case GGML_TYPE_IQ1_S:
-            {
-                GGML_ASSERT(start % QK_K == 0);
-                GGML_ASSERT(start % n_per_row == 0);
-                size_t start_row = start / n_per_row;
-                size_t row_size = ggml_row_size(type, n_per_row);
-                result = quantize_iq1_s(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix);
-                GGML_ASSERT(result == row_size * nrows);
-            } break;
-        case GGML_TYPE_IQ4_NL:
+        case GGML_TYPE_Q4_0:    result = quantize_q4_0(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
+        case GGML_TYPE_Q4_1:    result = quantize_q4_1(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
+        case GGML_TYPE_Q5_0:    result = quantize_q5_0(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
+        case GGML_TYPE_Q5_1:    result = quantize_q5_1(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
+        case GGML_TYPE_Q8_0:    result = quantize_q8_0(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
+        case GGML_TYPE_Q2_K:    result = quantize_q2_K(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
+        case GGML_TYPE_Q3_K:    result = quantize_q3_K(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
+        case GGML_TYPE_Q4_K:    result = quantize_q4_K(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
+        case GGML_TYPE_Q5_K:    result = quantize_q5_K(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
+        case GGML_TYPE_Q6_K:    result = quantize_q6_K(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
+        case GGML_TYPE_IQ2_XXS: result = quantize_iq2_xxs(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
+        case GGML_TYPE_IQ2_XS:  result = quantize_iq2_xs (src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
+        case GGML_TYPE_IQ3_XXS: result = quantize_iq3_xxs(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
+        case GGML_TYPE_IQ3_S:   result = quantize_iq3_s  (src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
+        case GGML_TYPE_IQ2_S:   result = quantize_iq2_s  (src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
+        case GGML_TYPE_IQ1_S:   result = quantize_iq1_s  (src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
+        case GGML_TYPE_IQ4_NL:  result = quantize_iq4_nl (src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
 #if QK_K == 64
-        case GGML_TYPE_IQ4_XS:
-#endif
-            {
-                GGML_ASSERT(start % QK4_NL == 0);
-                GGML_ASSERT(start % n_per_row == 0);
-                size_t start_row = start / n_per_row;
-                size_t row_size = ggml_row_size(type, n_per_row);
-                result = quantize_iq4_nl(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix);
-                GGML_ASSERT(result == row_size * nrows);
-            } break;
-#if QK_K != 64
-        case GGML_TYPE_IQ4_XS:
-            {
-                GGML_ASSERT(start % QK_K == 0);
-                GGML_ASSERT(start % n_per_row == 0);
-                size_t start_row = start / n_per_row;
-                size_t row_size = ggml_row_size(type, n_per_row);
-                result = quantize_iq4_xs(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix);
-                GGML_ASSERT(result == row_size * nrows);
-            } break;
+        case GGML_TYPE_IQ4_XS:  result = quantize_iq4_nl (src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
+#else
+        case GGML_TYPE_IQ4_XS:  result = quantize_iq4_xs (src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
 #endif
         case GGML_TYPE_F16:
             {
@@ -20481,6 +20229,9 @@ size_t ggml_quantize_chunk(enum ggml_type type, const float * src, void * dst, i
         default:
             assert(false);
     }
+
+    GGML_ASSERT(result == nrows * row_size);
+
     return result;
 }
 
diff --git a/ggml.h b/ggml.h
index 6e6cecebe..941398b77 100644
--- a/ggml.h
+++ b/ggml.h
@@ -2201,25 +2201,18 @@ extern "C" {
     GGML_API void ggml_quantize_init(enum ggml_type type);
     GGML_API void ggml_quantize_free(void);
 
-    // TODO: these would probably get removed in favor of the more general ggml_quantize_chunk
-    GGML_API size_t ggml_quantize_q4_0(const float * src, void * dst, int n, int k, int64_t * hist);
-    GGML_API size_t ggml_quantize_q4_1(const float * src, void * dst, int n, int k, int64_t * hist);
-    GGML_API size_t ggml_quantize_q5_0(const float * src, void * dst, int n, int k, int64_t * hist);
-    GGML_API size_t ggml_quantize_q5_1(const float * src, void * dst, int n, int k, int64_t * hist);
-    GGML_API size_t ggml_quantize_q8_0(const float * src, void * dst, int n, int k, int64_t * hist);
-
-    GGML_API size_t ggml_quantize_q2_K(const float * src, void * dst, int n, int k, int64_t * hist);
-    GGML_API size_t ggml_quantize_q3_K(const float * src, void * dst, int n, int k, int64_t * hist);
-    GGML_API size_t ggml_quantize_q4_K(const float * src, void * dst, int n, int k, int64_t * hist);
-    GGML_API size_t ggml_quantize_q5_K(const float * src, void * dst, int n, int k, int64_t * hist);
-    GGML_API size_t ggml_quantize_q6_K(const float * src, void * dst, int n, int k, int64_t * hist);
-
     // some quantization type cannot be used without an importance matrix
     GGML_API bool ggml_quantize_requires_imatrix(enum ggml_type type);
 
     // calls ggml_quantize_init internally (i.e. can allocate memory)
-    GGML_API size_t ggml_quantize_chunk(enum ggml_type type, const float * src, void * dst,
-            int start, int nrows, int n_per_row, int64_t * hist, const float * imatrix);
+    GGML_API size_t ggml_quantize_chunk(
+            enum ggml_type   type,
+               const float * src,
+                      void * dst,
+                       int   start,
+                       int   nrows,
+                       int   n_per_row,
+               const float * imatrix);
 
     //
     // gguf
diff --git a/llama.cpp b/llama.cpp
index 866330dcd..b5e0628d5 100644
--- a/llama.cpp
+++ b/llama.cpp
@@ -1772,6 +1772,7 @@ struct llama_cparams {
     float defrag_thold;
 
     bool embeddings;
+    bool causal_attn;
     bool offload_kqv;
 
     enum llama_pooling_type pooling_type;
@@ -4004,6 +4005,7 @@ static void llm_load_print_meta(llama_model_loader & ml, llama_model & model) {
     LLAMA_LOG_INFO("%s: n_ff             = %u\n",     __func__, hparams.n_ff);
     LLAMA_LOG_INFO("%s: n_expert         = %u\n",     __func__, hparams.n_expert);
     LLAMA_LOG_INFO("%s: n_expert_used    = %u\n",     __func__, hparams.n_expert_used);
+    LLAMA_LOG_INFO("%s: causal attm      = %d\n",     __func__, hparams.causal_attn);
     LLAMA_LOG_INFO("%s: pooling type     = %d\n",     __func__, hparams.pooling_type);
     LLAMA_LOG_INFO("%s: rope type        = %d\n",     __func__, hparams.rope_type);
     LLAMA_LOG_INFO("%s: rope scaling     = %s\n",     __func__, rope_scaling_type);
@@ -8604,7 +8606,13 @@ static void llama_set_inputs(llama_context & lctx, const llama_batch & batch) {
         ggml_backend_tensor_set(lctx.inp_pos, batch.pos, 0, n_tokens*ggml_element_size(lctx.inp_pos));
     }
 
-    if (hparams.causal_attn) {
+    GGML_ASSERT(
+        (hparams.causal_attn || !cparams.causal_attn) &&
+        "non-causal attention with generative models is not supported"
+    );
+
+    // NOTE: hparams.causal_attn indicates the model is capable of generation and uses the kv cache.
+    if (cparams.causal_attn) {
         const int64_t n_kv     = kv_self.n;
         const int64_t n_tokens = batch.n_tokens;
 
@@ -8632,8 +8640,9 @@ static void llama_set_inputs(llama_context & lctx, const llama_batch & batch) {
             }
         }
     } else {
-        // non-causal attention attends only the tokens within the batch (i.e. the KV cache is not used)
+        // when using kv cache, the mask needs to match the kv cache size
         const int64_t n_tokens = batch.n_tokens;
+        const int64_t n_stride = hparams.causal_attn ? kv_self.n : n_tokens;
 
         assert(ggml_backend_buffer_is_host(lctx.inp_KQ_mask->buffer));
 
@@ -8652,7 +8661,11 @@ static void llama_set_inputs(llama_context & lctx, const llama_batch & batch) {
                         }
                     }
 
-                    data[h*(n_tokens*n_tokens) + j*n_tokens + i] = f;
+                    data[h*(n_tokens*n_tokens) + j*n_stride + i] = f;
+                }
+
+                for (int i = n_tokens; i < n_stride; ++i) {
+                    data[h*(n_tokens*n_tokens) + j*n_stride + i] = -INFINITY;
                 }
             }
         }
@@ -8997,17 +9010,29 @@ static int llama_decode_internal(
 
         if (batch.logits) {
             logits_out.resize(n_vocab * n_tokens);
+            int32_t i_first = -1;
             for (uint32_t i = 0; i < n_tokens; i++) {
-                if (batch.logits[i] == 0) {
-                    continue;
+                if (batch.logits[i] && i_first == -1) {
+                    i_first = (int32_t) i;
+                }
+                if (batch.logits[i] == 0 || i == n_tokens - 1) {
+                    if (i_first != -1) {
+                        int i_last = batch.logits[i] == 0 ? i : i + 1;
+                        // extract logits for the range [i_first, i_last)
+                        // group the requests to minimize the number of calls to the backend
+                        ggml_backend_tensor_get_async(backend_res, res,
+                            logits_out.data() + (n_vocab*i_first),
+                            (n_vocab*i_first)*sizeof(float),
+                            (i_last - i_first)*n_vocab*sizeof(float));
+                        i_first = -1;
+                    }
                 }
-                ggml_backend_tensor_get_async(backend_res, res, logits_out.data() + (n_vocab*i), (n_vocab*i)*sizeof(float), n_vocab*sizeof(float));
 #ifndef NDEBUG
-                logits_valid[i] = true;
+                logits_valid[i] = batch.logits[i] != 0;
 #endif
             }
         } else if (lctx.logits_all) {
-            logits_out.resize(n_vocab * n_tokens);
+            logits_out.resize(n_vocab*n_tokens);
             ggml_backend_tensor_get_async(backend_res, res, logits_out.data(), 0, n_vocab*n_tokens*sizeof(float));
 #ifndef NDEBUG
             std::fill(logits_valid.begin(), logits_valid.end(), true);
@@ -11928,7 +11953,7 @@ static void llama_tensor_dequantize_internal(
     workers.clear();
 }
 
-static ggml_type get_k_quant_type(quantize_state_internal & qs, ggml_type new_type, const ggml_tensor * tensor, llama_ftype ftype) {
+static ggml_type llama_tensor_get_type(quantize_state_internal & qs, ggml_type new_type, const ggml_tensor * tensor, llama_ftype ftype) {
     const std::string name = ggml_get_name(tensor);
 
     // TODO: avoid hardcoded tensor names - use the TN_* constants
@@ -12207,17 +12232,16 @@ static ggml_type get_k_quant_type(quantize_state_internal & qs, ggml_type new_ty
     return new_type;
 }
 
-static int32_t llama_tensor_quantize_internal(enum ggml_type new_type, const float * f32_data, void * new_data, const int chunk_size, int nrows, int n_per_row, int64_t * hist_cur, const float * imatrix, std::vector<std::thread> & workers, const int nthread) {
+static int32_t llama_tensor_quantize_internal(enum ggml_type new_type, const float * f32_data, void * new_data, const int chunk_size, int nrows, int n_per_row, const float * imatrix, std::vector<std::thread> & workers, const int nthread) {
     std::mutex mutex;
     int counter = 0;
     size_t new_size = 0;
     if (nthread < 2) {
         // single-thread
-        return ggml_quantize_chunk(new_type, f32_data, new_data, 0, nrows, n_per_row, hist_cur, imatrix);
+        return ggml_quantize_chunk(new_type, f32_data, new_data, 0, nrows, n_per_row, imatrix);
     }
-    auto compute = [&mutex, &counter, &hist_cur, &new_size, new_type, f32_data, new_data, chunk_size,
+    auto compute = [&mutex, &counter, &new_size, new_type, f32_data, new_data, chunk_size,
             nrows, n_per_row, imatrix]() {
-        std::array<int64_t, 1 << 4> local_hist = {};
         const int nrows_per_chunk = chunk_size / n_per_row;
         size_t local_size = 0;
         while (true) {
@@ -12225,17 +12249,13 @@ static int32_t llama_tensor_quantize_internal(enum ggml_type new_type, const flo
             int first_row = counter; counter += nrows_per_chunk;
             if (first_row >= nrows) {
                 if (local_size > 0) {
-                    for (int j=0; j<int(local_hist.size()); ++j) {
-                        hist_cur[j] += local_hist[j];
-                    }
                     new_size += local_size;
                 }
                 break;
             }
             lock.unlock();
             const int this_nrow = std::min(nrows - first_row, nrows_per_chunk);
-            local_size += ggml_quantize_chunk(new_type, f32_data, new_data,
-                    first_row * n_per_row, this_nrow, n_per_row, local_hist.data(), imatrix);
+            local_size += ggml_quantize_chunk(new_type, f32_data, new_data, first_row * n_per_row, this_nrow, n_per_row, imatrix);
         }
     };
     for (int it = 0; it < nthread - 1; ++it) {
@@ -12248,40 +12268,40 @@ static int32_t llama_tensor_quantize_internal(enum ggml_type new_type, const flo
 }
 
 static void llama_model_quantize_internal(const std::string & fname_inp, const std::string & fname_out, const llama_model_quantize_params * params) {
-    ggml_type quantized_type;
+    ggml_type default_type;
     llama_ftype ftype = params->ftype;
 
     switch (params->ftype) {
-        case LLAMA_FTYPE_MOSTLY_Q4_0: quantized_type = GGML_TYPE_Q4_0; break;
-        case LLAMA_FTYPE_MOSTLY_Q4_1: quantized_type = GGML_TYPE_Q4_1; break;
-        case LLAMA_FTYPE_MOSTLY_Q5_0: quantized_type = GGML_TYPE_Q5_0; break;
-        case LLAMA_FTYPE_MOSTLY_Q5_1: quantized_type = GGML_TYPE_Q5_1; break;
-        case LLAMA_FTYPE_MOSTLY_Q8_0: quantized_type = GGML_TYPE_Q8_0; break;
-        case LLAMA_FTYPE_MOSTLY_F16:  quantized_type = GGML_TYPE_F16;  break;
-        case LLAMA_FTYPE_ALL_F32:     quantized_type = GGML_TYPE_F32;  break;
+        case LLAMA_FTYPE_MOSTLY_Q4_0: default_type = GGML_TYPE_Q4_0; break;
+        case LLAMA_FTYPE_MOSTLY_Q4_1: default_type = GGML_TYPE_Q4_1; break;
+        case LLAMA_FTYPE_MOSTLY_Q5_0: default_type = GGML_TYPE_Q5_0; break;
+        case LLAMA_FTYPE_MOSTLY_Q5_1: default_type = GGML_TYPE_Q5_1; break;
+        case LLAMA_FTYPE_MOSTLY_Q8_0: default_type = GGML_TYPE_Q8_0; break;
+        case LLAMA_FTYPE_MOSTLY_F16:  default_type = GGML_TYPE_F16;  break;
+        case LLAMA_FTYPE_ALL_F32:     default_type = GGML_TYPE_F32;  break;
 
         // K-quants
         case LLAMA_FTYPE_MOSTLY_Q2_K_S:
-        case LLAMA_FTYPE_MOSTLY_Q2_K:    quantized_type = GGML_TYPE_Q2_K;    break;
-        case LLAMA_FTYPE_MOSTLY_IQ3_XS:  quantized_type = GGML_TYPE_IQ3_S;   break;
+        case LLAMA_FTYPE_MOSTLY_Q2_K:    default_type = GGML_TYPE_Q2_K;    break;
+        case LLAMA_FTYPE_MOSTLY_IQ3_XS:  default_type = GGML_TYPE_IQ3_S;   break;
         case LLAMA_FTYPE_MOSTLY_Q3_K_S:
         case LLAMA_FTYPE_MOSTLY_Q3_K_M:
-        case LLAMA_FTYPE_MOSTLY_Q3_K_L:  quantized_type = GGML_TYPE_Q3_K;    break;
+        case LLAMA_FTYPE_MOSTLY_Q3_K_L:  default_type = GGML_TYPE_Q3_K;    break;
         case LLAMA_FTYPE_MOSTLY_Q4_K_S:
-        case LLAMA_FTYPE_MOSTLY_Q4_K_M:  quantized_type = GGML_TYPE_Q4_K;    break;
+        case LLAMA_FTYPE_MOSTLY_Q4_K_M:  default_type = GGML_TYPE_Q4_K;    break;
         case LLAMA_FTYPE_MOSTLY_Q5_K_S:
-        case LLAMA_FTYPE_MOSTLY_Q5_K_M:  quantized_type = GGML_TYPE_Q5_K;    break;
-        case LLAMA_FTYPE_MOSTLY_Q6_K:    quantized_type = GGML_TYPE_Q6_K;    break;
-        case LLAMA_FTYPE_MOSTLY_IQ2_XXS: quantized_type = GGML_TYPE_IQ2_XXS; break;
-        case LLAMA_FTYPE_MOSTLY_IQ2_XS:  quantized_type = GGML_TYPE_IQ2_XS;  break;
-        case LLAMA_FTYPE_MOSTLY_IQ2_S:   quantized_type = GGML_TYPE_IQ2_XS;  break;
-        case LLAMA_FTYPE_MOSTLY_IQ2_M:   quantized_type = GGML_TYPE_IQ2_S;   break;
-        case LLAMA_FTYPE_MOSTLY_IQ3_XXS: quantized_type = GGML_TYPE_IQ3_XXS; break;
-        case LLAMA_FTYPE_MOSTLY_IQ1_S:   quantized_type = GGML_TYPE_IQ1_S;   break;
-        case LLAMA_FTYPE_MOSTLY_IQ4_NL:  quantized_type = GGML_TYPE_IQ4_NL;  break;
-        case LLAMA_FTYPE_MOSTLY_IQ4_XS:  quantized_type = GGML_TYPE_IQ4_XS;  break;
-        case LLAMA_FTYPE_MOSTLY_IQ3_S:   quantized_type = GGML_TYPE_IQ3_S;   break;
-        case LLAMA_FTYPE_MOSTLY_IQ3_M:   quantized_type = GGML_TYPE_IQ3_S;   break;
+        case LLAMA_FTYPE_MOSTLY_Q5_K_M:  default_type = GGML_TYPE_Q5_K;    break;
+        case LLAMA_FTYPE_MOSTLY_Q6_K:    default_type = GGML_TYPE_Q6_K;    break;
+        case LLAMA_FTYPE_MOSTLY_IQ2_XXS: default_type = GGML_TYPE_IQ2_XXS; break;
+        case LLAMA_FTYPE_MOSTLY_IQ2_XS:  default_type = GGML_TYPE_IQ2_XS;  break;
+        case LLAMA_FTYPE_MOSTLY_IQ2_S:   default_type = GGML_TYPE_IQ2_XS;  break;
+        case LLAMA_FTYPE_MOSTLY_IQ2_M:   default_type = GGML_TYPE_IQ2_S;   break;
+        case LLAMA_FTYPE_MOSTLY_IQ3_XXS: default_type = GGML_TYPE_IQ3_XXS; break;
+        case LLAMA_FTYPE_MOSTLY_IQ1_S:   default_type = GGML_TYPE_IQ1_S;   break;
+        case LLAMA_FTYPE_MOSTLY_IQ4_NL:  default_type = GGML_TYPE_IQ4_NL;  break;
+        case LLAMA_FTYPE_MOSTLY_IQ4_XS:  default_type = GGML_TYPE_IQ4_XS;  break;
+        case LLAMA_FTYPE_MOSTLY_IQ3_S:   default_type = GGML_TYPE_IQ3_S;   break;
+        case LLAMA_FTYPE_MOSTLY_IQ3_M:   default_type = GGML_TYPE_IQ3_S;   break;
 
         default: throw std::runtime_error(format("invalid output file type %d\n", ftype));
     }
@@ -12358,7 +12378,6 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s
 
     size_t total_size_org = 0;
     size_t total_size_new = 0;
-    std::vector<int64_t> hist_all(1 << 4, 0);
 
     std::vector<std::thread> workers;
     workers.reserve(nthread);
@@ -12423,23 +12442,26 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s
         // do not quantize Mamba's small yet 2D weights
         // NOTE: can't use LLM_TN here because the layer number is not known
         quantize &= name.find("ssm_conv1d.weight") == std::string::npos;
-        quantize &= name.find("ssm_x.weight") == std::string::npos;
-        quantize &= name.find("ssm_dt.weight") == std::string::npos;
+        quantize &= name.find("ssm_x.weight")      == std::string::npos;
+        quantize &= name.find("ssm_dt.weight")     == std::string::npos;
 
         enum ggml_type new_type;
         void * new_data;
         size_t new_size;
 
         if (quantize) {
-            new_type = quantized_type;
-            if (!params->pure) {
-                new_type = get_k_quant_type(qs, new_type, tensor, ftype);
+            new_type = default_type;
+
+            // get more optimal quantization type based on the tensor shape, layer, etc.
+            if (!params->pure && ggml_is_quantized(default_type)) {
+                new_type = llama_tensor_get_type(qs, new_type, tensor, ftype);
             }
 
             // If we've decided to quantize to the same type the tensor is already
             // in then there's nothing to do.
             quantize = tensor->type != new_type;
         }
+
         if (!quantize) {
             new_type = tensor->type;
             new_data = tensor->data;
@@ -12485,14 +12507,13 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s
                 f32_data = (float *) f32_conv_buf.data();
             }
 
-            LLAMA_LOG_INFO("quantizing to %s .. ", ggml_type_name(new_type));
+            LLAMA_LOG_INFO("converting to %s .. ", ggml_type_name(new_type));
             fflush(stdout);
 
             if (work.size() < nelements * 4) {
                 work.resize(nelements * 4); // upper bound on size
             }
             new_data = work.data();
-            std::array<int64_t, 1 << 4> hist_cur = {};
 
             const int n_per_row = tensor->ne[0];
             const int nrows = nelements / n_per_row;
@@ -12502,22 +12523,9 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s
 
             const int nchunk = (nelements + chunk_size - 1)/chunk_size;
             const int nthread_use = nthread > 1 ? std::max(1, std::min(nthread, nchunk)) : 1;
-            new_size = llama_tensor_quantize_internal(new_type, f32_data, new_data, chunk_size, nrows, n_per_row, hist_cur.data(), imatrix, workers, nthread_use);
+            new_size = llama_tensor_quantize_internal(new_type, f32_data, new_data, chunk_size, nrows, n_per_row, imatrix, workers, nthread_use);
 
-            LLAMA_LOG_INFO("size = %8.2f MiB -> %8.2f MiB", ggml_nbytes(tensor)/1024.0/1024.0, new_size/1024.0/1024.0);
-            int64_t tot_count = 0;
-            for (size_t i = 0; i < hist_cur.size(); i++) {
-                hist_all[i] += hist_cur[i];
-                tot_count += hist_cur[i];
-            }
-
-            if (tot_count > 0) {
-                LLAMA_LOG_INFO(" | hist: ");
-                for (size_t i = 0; i < hist_cur.size(); i++) {
-                    LLAMA_LOG_INFO("%5.3f ", hist_cur[i] / float(nelements));
-                }
-            }
-            LLAMA_LOG_INFO("\n");
+            LLAMA_LOG_INFO("size = %8.2f MiB -> %8.2f MiB\n", ggml_nbytes(tensor)/1024.0/1024.0, new_size/1024.0/1024.0);
         }
         total_size_org += ggml_nbytes(tensor);
         total_size_new += new_size;
@@ -12546,24 +12554,8 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s
     LLAMA_LOG_INFO("%s: model size  = %8.2f MB\n", __func__, total_size_org/1024.0/1024.0);
     LLAMA_LOG_INFO("%s: quant size  = %8.2f MB\n", __func__, total_size_new/1024.0/1024.0);
 
-    // print histogram for all tensors
-    {
-        int64_t sum_all = 0;
-        for (size_t i = 0; i < hist_all.size(); i++) {
-            sum_all += hist_all[i];
-        }
-
-        if (sum_all > 0) {
-            LLAMA_LOG_INFO("%s: hist: ", __func__);
-            for (size_t i = 0; i < hist_all.size(); i++) {
-                LLAMA_LOG_INFO("%5.3f ", hist_all[i] / float(sum_all));
-            }
-            LLAMA_LOG_INFO("\n");
-        }
-    }
-
     if (qs.n_fallback > 0) {
-        LLAMA_LOG_WARN("%s: WARNING: %d of %d tensor(s) incompatible with k-quants and required fallback quantization\n",
+        LLAMA_LOG_WARN("%s: WARNING: %d of %d tensor(s) required fallback quantization\n",
                 __func__, qs.n_fallback, qs.n_k_quantized + qs.n_fallback);
     }
 }
@@ -13064,6 +13056,8 @@ struct llama_context * llama_new_context_with_model(
         cparams.yarn_ext_factor = rope_scaling_type == LLAMA_ROPE_SCALING_TYPE_YARN ? 1.0f : 0.0f;
     }
 
+    cparams.causal_attn = hparams.causal_attn;
+
     if (cparams.pooling_type == LLAMA_POOLING_TYPE_UNSPECIFIED) {
         if (hparams.pooling_type == LLAMA_POOLING_TYPE_UNSPECIFIED) {
             cparams.pooling_type = LLAMA_POOLING_TYPE_NONE;
@@ -14108,6 +14102,10 @@ void llama_set_abort_callback(struct llama_context * ctx, bool (*abort_callback)
     ctx->abort_callback_data = abort_callback_data;
 }
 
+void llama_set_causal_attn(struct llama_context * ctx, bool causal_attn) {
+    ctx->cparams.causal_attn = causal_attn;
+}
+
 struct llama_batch llama_batch_get_one(
              llama_token * tokens,
                  int32_t   n_tokens,
@@ -14304,7 +14302,7 @@ int32_t llama_token_to_piece(const struct llama_model * model, llama_token token
             } else if (llama_is_user_defined_token(model->vocab, token)) {
                 std::string result = model->vocab.id_to_token[token].text;
                 if (length < (int) result.length()) {
-                    return -result.length();
+                    return -(int) result.length();
                 }
                 memcpy(buf, result.c_str(), result.length());
                 return result.length();
@@ -14339,7 +14337,7 @@ int32_t llama_token_to_piece(const struct llama_model * model, llama_token token
             } else if (llama_is_user_defined_token(model->vocab, token)) {
                 std::string result = model->vocab.id_to_token[token].text;
                 if (length < (int) result.length()) {
-                    return -result.length();
+                    return -(int) result.length();
                 }
                 memcpy(buf, result.c_str(), result.length());
                 return result.length();
diff --git a/llama.h b/llama.h
index d659b22d5..439f8adf5 100644
--- a/llama.h
+++ b/llama.h
@@ -278,7 +278,7 @@ extern "C" {
         bool allow_requantize;       // allow quantizing non-f32/f16 tensors
         bool quantize_output_tensor; // quantize output.weight
         bool only_copy;              // only copy tensors - ftype, allow_requantize and quantize_output_tensor are ignored
-        bool pure;                   // disable k-quant mixtures and quantize all tensors to the same type
+        bool pure;                   // quantize all tensors to the default type
         void * imatrix;              // pointer to importance matrix data
     } llama_model_quantize_params;
 
@@ -645,6 +645,10 @@ extern "C" {
     // n_threads_batch is the number of threads used for prompt and batch processing (multiple tokens)
     LLAMA_API void llama_set_n_threads(struct llama_context * ctx, uint32_t n_threads, uint32_t n_threads_batch);
 
+    // Set whether to use causal attention or not
+    // If set to true, the model will only attend to the past tokens
+    LLAMA_API void llama_set_causal_attn(struct llama_context * ctx, bool causal_attn);
+
     // Set abort callback
     LLAMA_API void llama_set_abort_callback(struct llama_context * ctx, ggml_abort_callback abort_callback, void * abort_callback_data);
 
diff --git a/otherarch/sdcpp/model.cpp b/otherarch/sdcpp/model.cpp
index 58cdd939a..07ed53d19 100644
--- a/otherarch/sdcpp/model.cpp
+++ b/otherarch/sdcpp/model.cpp
@@ -515,7 +515,7 @@ void convert_tensor(void* src,
             int64_t hist[16];
             std::vector<float> imatrix(n_per_row, 1.0f);  // dummy importance matrix
             const float* im = imatrix.data();
-            ggml_quantize_chunk(dst_type, (float*)src, dst, 0, nrows, n_per_row, hist, im);
+            ggml_quantize_chunk(dst_type, (float*)src, dst, 0, nrows, n_per_row, im);
         }
     } else if (dst_type == GGML_TYPE_F32) {
         if (src_type == GGML_TYPE_F16) {
@@ -546,7 +546,7 @@ void convert_tensor(void* src,
             int64_t hist[16];
             std::vector<float> imatrix(n_per_row, 1.0f);  // dummy importance matrix
             const float* im = imatrix.data();
-            ggml_quantize_chunk(dst_type, (float*)src_data_f32, dst, 0, nrows, n_per_row, hist, im);
+            ggml_quantize_chunk(dst_type, (float*)src_data_f32, dst, 0, nrows, n_per_row, im);
         }
     }
 }