EngineX-Ascend/enginex-ascend-910-llama.cpp
10
0
Fork 0
Code Issues Pull Requests Actions 4 Projects Releases Wiki Activity

musa: Upgrade MUSA SDK version to rc4.0.1 and use mudnn::Unary::IDENTITY op to accelerate D2D memory copy (#13647)

Browse Source 
* musa: fix build warning (unused parameter)

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>

* musa: upgrade MUSA SDK version to rc4.0.1

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>

* musa: use mudnn::Unary::IDENTITY op to accelerate D2D memory copy

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>

* Update ggml/src/ggml-cuda/cpy.cu

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

* musa: remove MUDNN_CHECK_GEN and use CUDA_CHECK_GEN instead in MUDNN_CHECK

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>

---------

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
This commit is contained in:
R0CKSTAR
2025-05-21 09:58:49 +08:00
committed by GitHub
parent fb1cab201c
commit 33983057d0
10 changed files with 153 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
ggml/src/ggml-musa/CMakeLists.txt
View File

@@ -27,12 +27,15 @@ if (MUSAToolkit_FOUND)
file(GLOB GGML_HEADERS_MUSA "../ggml-cuda/*.cuh")
list(APPEND GGML_HEADERS_MUSA "../../include/ggml-cuda.h")
list(APPEND GGML_HEADERS_MUSA "../ggml-musa/mudnn.cuh")
file(GLOB GGML_SOURCES_MUSA "../ggml-cuda/*.cu")
file(GLOB SRCS "../ggml-cuda/template-instances/fattn-mma*.cu")
list(APPEND GGML_SOURCES_MUSA ${SRCS})
file(GLOB SRCS "../ggml-cuda/template-instances/mmq*.cu")
list(APPEND GGML_SOURCES_MUSA ${SRCS})
file(GLOB SRCS "../ggml-musa/*.cu")
list(APPEND GGML_SOURCES_MUSA ${SRCS})
if (GGML_CUDA_FA_ALL_QUANTS)
file(GLOB SRCS "../ggml-cuda/template-instances/fattn-vec*.cu")
@@ -62,7 +65,9 @@ if (MUSAToolkit_FOUND)
)
# TODO: do not use CUDA definitions for MUSA
target_compile_definitions(ggml PUBLIC GGML_USE_CUDA)
if (NOT GGML_BACKEND_DL)
target_compile_definitions(ggml PUBLIC GGML_USE_CUDA)
endif()
add_compile_definitions(GGML_USE_MUSA)
add_compile_definitions(GGML_CUDA_PEER_MAX_BATCH_SIZE=${GGML_CUDA_PEER_MAX_BATCH_SIZE})
@@ -92,9 +97,10 @@ if (MUSAToolkit_FOUND)
endif()
if (GGML_STATIC)
# TODO: mudnn has not provided static libraries yet
target_link_libraries(ggml-musa PRIVATE MUSA::musart_static MUSA::mublas_static)
else()
target_link_libraries(ggml-musa PRIVATE MUSA::musart MUSA::mublas)
target_link_libraries(ggml-musa PRIVATE MUSA::musart MUSA::mublas mudnn)
endif()
if (GGML_CUDA_NO_VMM)