tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-13 20:07:41 -04:00
Code Issues Packages Projects Releases Wiki Activity

HIP: add cmake option to enable compiler output of kernel resource usage metrics (#15103)

Browse Source
This commit is contained in:
uvos
2025-08-07 16:44:14 +02:00
committed by GitHub
parent 9a96389544
commit 7ad67ba9fe
2 changed files with 5 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
ggml/CMakeLists.txt
View File

@@ -176,6 +176,7 @@ option(GGML_HIP_NO_VMM "ggml: do not try to use HIP VMM"
option(GGML_HIP_ROCWMMA_FATTN "ggml: enable rocWMMA for FlashAttention" OFF)
option(GGML_HIP_FORCE_ROCWMMA_FATTN_GFX12 "ggml: enable rocWMMA FlashAttention on GFX12" OFF)
option(GGML_HIP_MMQ_MFMA "ggml: enable MFMA MMA for CDNA in MMQ" ON)
option(GGML_HIP_EXPORT_METRICS "ggml: enable kernel perf metrics output" OFF)
option(GGML_MUSA_GRAPHS "ggml: use MUSA graph, experimental, unstable" OFF)
option(GGML_MUSA_MUDNN_COPY "ggml: enable muDNN for accelerated copy" OFF)
option(GGML_VULKAN "ggml: use Vulkan" OFF)

4
ggml/src/ggml-hip/CMakeLists.txt
View File

@@ -121,6 +121,10 @@ if (GGML_HIP_FORCE_ROCWMMA_FATTN_GFX12 OR ${hip_VERSION} VERSION_GREATER_EQUAL 7
add_compile_definitions(GGML_HIP_ROCWMMA_FATTN_GFX12)
endif()
if (GGML_HIP_EXPORT_METRICS)
set(CMAKE_HIP_FLAGS "${CMAKE_HIP_FLAGS} -Rpass-analysis=kernel-resource-usage --save-temps")
endif()
if (NOT GGML_CUDA_FA)
add_compile_definitions(GGML_CUDA_NO_FA)
endif()