Merge branch 'upstream' into concedo_experimental

# Conflicts:
#	.devops/cann.Dockerfile
#	.github/workflows/build.yml
#	.github/workflows/release.yml
#	.gitignore
#	README.md
#	common/CMakeLists.txt
#	docs/ops.md
#	docs/ops/Vulkan.csv
#	examples/eval-callback/eval-callback.cpp
#	ggml/src/ggml-cann/aclnn_ops.cpp
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-cpu/arch/x86/repack.cpp
#	ggml/src/ggml-cpu/kleidiai/kernels.cpp
#	scripts/sync-ggml.last
#	src/llama-grammar.cpp
#	tests/test-backend-ops.cpp
#	tests/test-chat.cpp
#	tools/server/CMakeLists.txt

tools/main/main.cpp

@@ -148,11 +148,15 @@ int main(int argc, char ** argv) {
         return 1;
     }
 
-    auto * mem = llama_get_memory(ctx);
-
+    llama_memory_t mem = llama_get_memory(ctx);
     const llama_vocab * vocab = llama_model_get_vocab(model);
+
+    // note: the time for chat template initialization is not negligible:
     auto chat_templates = common_chat_templates_init(model, params.chat_template);
 
+    // start measuring performance timings from here
+    llama_perf_context_reset(ctx);
+
     LOG_INF("%s: llama threadpool init, n_threads = %d\n", __func__, (int) params.cpuparams.n_threads);
 
     auto * cpu_dev = ggml_backend_dev_by_type(GGML_BACKEND_DEVICE_TYPE_CPU);