Merge commit 'fbd441c379' into concedo_experimental

# Conflicts:
#	.github/workflows/build.yml
#	AGENTS.md
#	ci/run.sh
#	docs/build.md
#	embd_res/templates/LFM2.5-Instruct.jinja
#	ggml/CMakeLists.txt
#	ggml/src/ggml-cuda/fattn.cu
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp/CMakeLists.txt
#	ggml/src/ggml-hexagon/htp/htp-msg.h
#	ggml/src/ggml-hexagon/htp/htp-ops.h
#	ggml/src/ggml-hexagon/htp/hvx-div.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hexagon/htp/unary-ops.c
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-sycl/common.hpp
#	ggml/src/ggml-sycl/convert.cpp
#	ggml/src/ggml-sycl/dequantize.hpp
#	ggml/src/ggml-sycl/mmvq.cpp
#	ggml/src/ggml-sycl/vecdotq.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-webgpu/wgsl-shaders/common_decls.tmpl
#	ggml/src/ggml-webgpu/wgsl-shaders/flash_attn.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_decls.tmpl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_vec.wgsl
#	scripts/hip/gcn-cdna-vgpr-check.py
#	scripts/sync-ggml.last
#	tests/test-chat.cpp

tools/quantize/quantize.cpp

@@ -14,13 +14,10 @@
 #include <unordered_map>
 #include <map>
 #include <fstream>
-#include <cmath>
-#include <cctype>
-#include <algorithm>
 #include <filesystem>
 
 // result of parsing --tensor-type option
-// (changes to this struct must be reflected in src/llama-quant.cpp)
+// changes to this struct must also be reflected in src/llama-quant.cpp
 struct tensor_type_option {
     std::string name;
     ggml_type type = GGML_TYPE_COUNT;
@@ -492,7 +489,6 @@ static bool parse_layer_prune(const char * data, std::vector<int> & prune_layers
 
 int main(int argc, char ** argv) {
     std::setlocale(LC_NUMERIC, "C");
-
     if (argc < 3) {
         usage(argv[0]);
     }
@@ -585,8 +581,16 @@ int main(int argc, char ** argv) {
     std::vector<std::string> imatrix_datasets;
     std::unordered_map<std::string, std::vector<float>> imatrix_data;
     int m_last_call = prepare_imatrix(imatrix_file, imatrix_datasets, included_weights, excluded_weights, imatrix_data);
+
+    std::vector<llama_model_imatrix_data> i_data;
+    std::vector<llama_model_tensor_override> t_override;
     if (!imatrix_data.empty()) {
-        params.imatrix = &imatrix_data;
+        i_data.reserve(imatrix_data.size() + 1);
+        for (const auto & kv : imatrix_data) {
+            i_data.push_back({kv.first.c_str(), kv.second.data(), kv.second.size()});
+        }
+        i_data.push_back({nullptr, nullptr, 0});  // array terminator
+        params.imatrix = i_data.data();
         {
             llama_model_kv_override kvo;
             std::strcpy(kvo.key, LLM_KV_QUANTIZE_IMATRIX_FILE);
@@ -604,7 +608,6 @@ int main(int argc, char ** argv) {
             kvo.val_str[127] = '\0';
             kv_overrides.emplace_back(std::move(kvo));
         }
-
         {
             llama_model_kv_override kvo;
             std::strcpy(kvo.key, LLM_KV_QUANTIZE_IMATRIX_N_ENTRIES);
@@ -612,7 +615,6 @@ int main(int argc, char ** argv) {
             kvo.val_i64 = imatrix_data.size();
             kv_overrides.emplace_back(std::move(kvo));
         }
-
         if (m_last_call > 0) {
             llama_model_kv_override kvo;
             std::strcpy(kvo.key, LLM_KV_QUANTIZE_IMATRIX_N_CHUNKS);
@@ -624,13 +626,19 @@ int main(int argc, char ** argv) {
     if (!kv_overrides.empty()) {
         kv_overrides.emplace_back();
         kv_overrides.back().key[0] = 0;
-        params.kv_overrides = &kv_overrides;
+        params.kv_overrides = kv_overrides.data();
     }
     if (!tensor_type_opts.empty()) {
-        params.tensor_types = &tensor_type_opts;
+        t_override.reserve(tensor_type_opts.size() + 1);
+        for (const auto & tt : tensor_type_opts) {
+            t_override.push_back({tt.name.c_str(), tt.type});
+        }
+        t_override.push_back({nullptr, GGML_TYPE_COUNT});  // array terminator
+        params.tt_overrides = t_override.data();
     }
     if (!prune_layers.empty()) {
-        params.prune_layers = &prune_layers;
+        prune_layers.push_back(-1);  // array terminator
+        params.prune_layers = prune_layers.data();
     }
 
     llama_backend_init();