Merge commit '8f47e25f56' into concedo_experimental

# Conflicts:
#	.github/labeler.yml
#	.github/workflows/build-linux-cross.yml
#	docs/backend/CANN.md
#	examples/batched.swift/Sources/main.swift
#	examples/embedding/embedding.cpp
#	examples/gritlm/gritlm.cpp
#	examples/llama.android/llama/src/main/cpp/llama-android.cpp
#	examples/llama.swiftui/llama.cpp.swift/LibLlama.swift
#	examples/lookahead/lookahead.cpp
#	examples/lookup/lookup.cpp
#	examples/parallel/parallel.cpp
#	examples/passkey/passkey.cpp
#	examples/retrieval/retrieval.cpp
#	examples/save-load-state/save-load-state.cpp
#	examples/simple-chat/simple-chat.cpp
#	examples/speculative-simple/speculative-simple.cpp
#	examples/speculative/speculative.cpp
#	ggml/src/ggml-cann/common.h
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-sycl/convert.cpp
#	ggml/src/ggml-sycl/cpy.cpp
#	ggml/src/ggml-sycl/dequantize.hpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/mmvq.cpp
#	ggml/src/ggml-sycl/vecdotq.hpp
#	tools/batched-bench/batched-bench.cpp
#	tools/cvector-generator/cvector-generator.cpp
#	tools/imatrix/imatrix.cpp
#	tools/llama-bench/llama-bench.cpp
#	tools/perplexity/perplexity.cpp
#	tools/run/run.cpp

src/llama-kv-cache-recurrent.cpp

@@ -117,18 +117,21 @@ llama_kv_cache_recurrent::llama_kv_cache_recurrent(
     }
 }
 
-void llama_kv_cache_recurrent::clear() {
+void llama_kv_cache_recurrent::clear(bool data) {
     for (int32_t i = 0; i < (int32_t) size; ++i) {
         cells[i].pos = -1;
         cells[i].seq_id.clear();
         cells[i].src = -1;
         cells[i].tail = -1;
     }
+
     head = 0;
     used = 0;
 
-    for (auto & buf : bufs) {
-        ggml_backend_buffer_clear(buf.get(), 0);
+    if (data) {
+        for (auto & buf : bufs) {
+            ggml_backend_buffer_clear(buf.get(), 0);
+        }
     }
 }
 
@@ -723,7 +726,7 @@ void llama_kv_cache_recurrent::state_read(llama_io_read_i & io, llama_seq_id seq
 
     if (!res) {
         if (seq_id == -1) {
-            clear();
+            clear(true);
         } else {
             seq_rm(seq_id, -1, -1);
         }
@@ -880,7 +883,7 @@ bool llama_kv_cache_recurrent::state_read_meta(llama_io_read_i & io, uint32_t ce
             return false;
         }
 
-        clear();
+        clear(true);
 
         for (uint32_t i = 0; i < cell_count; ++i) {
             kv_cell & cell = cells[i];