vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

feat: Support Moore Threads GPU (#8383)

Browse source 
* Update doc for MUSA

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

* Add GGML_MUSA in Makefile

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

* Add GGML_MUSA in CMake

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

* CUDA => MUSA

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

* MUSA adds support for __vsubss4

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

* Fix CI build failure

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

---------

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
This commit is contained in:
R0CKSTAR 2024-07-28 07:41:25 +08:00 • committed by GitHub
parent 5e2727fe03
commit e54c35e4fb
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
9 changed files with 329 additions and 30 deletions
Download patch file Download diff file Expand all files Collapse all files

62
ggml/src/CMakeLists.txt
View file

@ -139,6 +139,17 @@ if (GGML_METAL)
)
endif()
if (GGML_MUSA)
set(CMAKE_C_COMPILER clang)
set(CMAKE_C_EXTENSIONS OFF)
set(CMAKE_CXX_COMPILER clang++)
set(CMAKE_CXX_EXTENSIONS OFF)
set(GGML_CUDA ON)
list(APPEND GGML_CDEF_PUBLIC GGML_USE_MUSA)
endif()
if (GGML_OPENMP)
find_package(OpenMP)
if (OpenMP_FOUND)
@ -147,6 +158,11 @@ if (GGML_OPENMP)
add_compile_definitions(GGML_USE_OPENMP)
set(GGML_EXTRA_LIBS ${GGML_EXTRA_LIBS} OpenMP::OpenMP_C OpenMP::OpenMP_CXX)
if (GGML_MUSA)
set(GGML_EXTRA_INCLUDES ${GGML_EXTRA_INCLUDES} "/usr/lib/llvm-10/include/openmp")
set(GGML_EXTRA_LIBS ${GGML_EXTRA_LIBS} "/usr/lib/llvm-10/lib/libomp.so")
endif()
else()
message(WARNING "OpenMP not found")
endif()
@ -249,7 +265,13 @@ endif()
if (GGML_CUDA)
cmake_minimum_required(VERSION 3.18) # for CMAKE_CUDA_ARCHITECTURES
find_package(CUDAToolkit)
if (GGML_MUSA)
list(APPEND CMAKE_MODULE_PATH "/usr/local/musa/cmake/")
find_package(MUSAToolkit)
set(CUDAToolkit_FOUND ${MUSAToolkit_FOUND})
else()
find_package(CUDAToolkit)
endif()
if (CUDAToolkit_FOUND)
message(STATUS "CUDA found")
@ -268,7 +290,11 @@ if (GGML_CUDA)
endif()
message(STATUS "Using CUDA architectures: ${CMAKE_CUDA_ARCHITECTURES}")
enable_language(CUDA)
if (GGML_MUSA)
set(CMAKE_CUDA_COMPILER ${MUSAToolkit_MCC_EXECUTABLE})
else()
enable_language(CUDA)
endif()
file(GLOB GGML_HEADERS_CUDA "ggml-cuda/*.cuh")
list(APPEND GGML_HEADERS_CUDA "../include/ggml-cuda.h")
@ -332,21 +358,40 @@ if (GGML_CUDA)
add_compile_definitions(GGML_CUDA_NO_PEER_COPY)
endif()
if (GGML_MUSA)
set_source_files_properties(${GGML_SOURCES_CUDA} PROPERTIES LANGUAGE CXX)
foreach(SOURCE ${GGML_SOURCES_CUDA})
set_property(SOURCE ${SOURCE} PROPERTY COMPILE_FLAGS "-x musa -mtgpu --cuda-gpu-arch=mp_22")
endforeach()
endif()
if (GGML_STATIC)
if (WIN32)
# As of 12.3.1 CUDA Toolkit for Windows does not offer a static cublas library
set(GGML_EXTRA_LIBS ${GGML_EXTRA_LIBS} CUDA::cudart_static CUDA::cublas CUDA::cublasLt)
else ()
set(GGML_EXTRA_LIBS ${GGML_EXTRA_LIBS} CUDA::cudart_static CUDA::cublas_static CUDA::cublasLt_static)
if (GGML_MUSA)
set(GGML_EXTRA_LIBS ${GGML_EXTRA_LIBS} MUSA::musart_static MUSA::mublas_static)
else()
set(GGML_EXTRA_LIBS ${GGML_EXTRA_LIBS} CUDA::cudart_static CUDA::cublas_static CUDA::cublasLt_static)
endif()
endif()
else()
set(GGML_EXTRA_LIBS ${GGML_EXTRA_LIBS} CUDA::cudart CUDA::cublas CUDA::cublasLt)
if (GGML_MUSA)
set(GGML_EXTRA_LIBS ${GGML_EXTRA_LIBS} MUSA::musart MUSA::mublas)
else()
set(GGML_EXTRA_LIBS ${GGML_EXTRA_LIBS} CUDA::cudart CUDA::cublas CUDA::cublasLt)
endif()
endif()
if (GGML_CUDA_NO_VMM)
# No VMM requested, no need to link directly with the cuda driver lib (libcuda.so)
else()
set(GGML_EXTRA_LIBS ${GGML_EXTRA_LIBS} CUDA::cuda_driver) # required by cuDeviceGetAttribute(), cuMemGetAllocationGranularity(...), ...
if (GGML_MUSA)
set(GGML_EXTRA_LIBS ${GGML_EXTRA_LIBS} MUSA::musa_driver) # required by muDeviceGetAttribute(), muMemGetAllocationGranularity(...), ...
else()
set(GGML_EXTRA_LIBS ${GGML_EXTRA_LIBS} CUDA::cuda_driver) # required by cuDeviceGetAttribute(), cuMemGetAllocationGranularity(...), ...
endif()
endif()
else()
message(WARNING "CUDA not found")
@ -857,8 +902,10 @@ function(get_flags CCID CCVER)
set(C_FLAGS -Wdouble-promotion)
set(CXX_FLAGS -Wno-array-bounds)
if (CCVER VERSION_GREATER_EQUAL 7.1.0)
list(APPEND CXX_FLAGS -Wno-format-truncation)
if (NOT GGML_MUSA)
if (CCVER VERSION_GREATER_EQUAL 7.1.0)
list(APPEND CXX_FLAGS -Wno-format-truncation)
endif()
endif()
if (CCVER VERSION_GREATER_EQUAL 8.1.0)
list(APPEND CXX_FLAGS -Wextra-semi)
@ -1264,6 +1311,7 @@ endif()
target_compile_definitions(ggml PUBLIC ${GGML_CDEF_PUBLIC})
target_include_directories(ggml PUBLIC ../include)
target_include_directories(ggml PRIVATE . ${GGML_EXTRA_INCLUDES})
target_link_directories(ggml PRIVATE ${GGML_EXTRA_LIBDIRS})
target_compile_features (ggml PRIVATE c_std_11) # don't bump
target_link_libraries(ggml PRIVATE Threads::Threads ${GGML_EXTRA_LIBS})