Merge commit '9e54e687cbc1500e2097be5b849c03bdc9de6610' into concedo_experimental

# Conflicts:
#	docs/backend/snapdragon/windows.md
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp-drv.cpp
#	ggml/src/ggml-hexagon/htp-drv.h
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-sycl/fattn-common.hpp
#	ggml/src/ggml-sycl/fattn-onednn.cpp
#	ggml/src/ggml-sycl/fattn-onednn.hpp
#	ggml/src/ggml-sycl/fattn.cpp
#	ggml/src/ggml-sycl/fattn.hpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-virtgpu/ggml-backend.cpp
#	scripts/snapdragon/build.py
#	tests/test-alloc.cpp
#	tests/test-backend-ops.cpp
#	tools/llama-bench/README.md
#	tools/llama-bench/llama-bench.cpp

include/llama.h

@@ -217,10 +217,10 @@ extern "C" {
     LLAMA_API const char * llama_load_mode_name(enum llama_load_mode load_mode);
     LLAMA_API enum llama_load_mode llama_load_mode_from_str(const char * str);
 
-    enum llama_tensor_read_lazy {
-        LLAMA_TENSOR_READ_LAZY_OFF  = 0, // always read the whole tensor up front
-        LLAMA_TENSOR_READ_LAZY_AUTO = 1, // lazy only for marked tensors larger than 4 GiB (requires mmap)
-        LLAMA_TENSOR_READ_LAZY_ON   = 2, // read the rows of tensors marked by the arch on demand (requires mmap)
+    enum llama_lazy_mode {
+        LLAMA_LAZY_MODE_OFF  = 0, // always read the whole tensor up front
+        LLAMA_LAZY_MODE_AUTO = 1, // lazy only for marked tensors larger than 4 GiB (requires mmap)
+        LLAMA_LAZY_MODE_ON   = 2, // read the rows of tensors marked by the arch on demand (requires mmap)
     };
 
     enum llama_context_type {
@@ -324,7 +324,7 @@ extern "C" {
         enum llama_split_mode split_mode; // how to split the model across multiple GPUs
         enum llama_load_mode  load_mode;  // how to load the model
 
-        enum llama_tensor_read_lazy tensor_read_lazy; // on-demand reading of tensors marked by the arch
+        enum llama_lazy_mode lazy_mode; // on-demand reading of tensors marked by the arch
 
         // the GPU that is used for the entire model when split_mode is LLAMA_SPLIT_MODE_NONE
         int32_t main_gpu;