Merge branch 'upstream' into concedo_experimental

# Conflicts:
#	.github/workflows/build.yml
#	Makefile
#	README.md
#	docs/backend/SYCL.md
#	examples/llava/README.md
#	examples/llava/clip.cpp
#	examples/run/run.cpp
#	examples/server/README.md
#	examples/sycl/run-llama2.sh
#	ggml/CMakeLists.txt
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-cuda/CMakeLists.txt
#	ggml/src/ggml-hip/CMakeLists.txt
#	ggml/src/ggml-musa/CMakeLists.txt
#	ggml/src/ggml-sycl/CMakeLists.txt
#	tests/test-backend-ops.cpp

include/llama.h

@@ -479,6 +479,7 @@ extern "C" {
     LLAMA_API int32_t llama_model_n_embd     (const struct llama_model * model);
     LLAMA_API int32_t llama_model_n_layer    (const struct llama_model * model);
     LLAMA_API int32_t llama_model_n_head     (const struct llama_model * model);
+    LLAMA_API int32_t llama_model_n_head_kv  (const struct llama_model * model);
 
     // Get the model's RoPE frequency scaling factor
     LLAMA_API float llama_model_rope_freq_scale_train(const struct llama_model * model);