[CPU] Refactor CPU W8A8 scaled_mm (#23071)

Signed-off-by: jiang1.li <jiang1.li@intel.com>
This commit is contained in:
Li, Jiang
2025-08-21 09:34:24 +08:00
committed by GitHub
parent b029de9902
commit 7be5d113d8
17 changed files with 1525 additions and 1273 deletions

View File

@@ -182,17 +182,17 @@ endif()
#
# Build oneDNN for W8A8 GEMM kernels (only for x86-AVX512 /ARM platforms)
# Flag to enable ACL kernels for AARCH64 platforms
if ( VLLM_BUILD_ACL STREQUAL "ON")
if (VLLM_BUILD_ACL STREQUAL "ON")
set(USE_ACL ON)
else()
set(USE_ACL OFF)
endif()
if ((AVX512_FOUND AND NOT AVX512_DISABLED) OR ASIMD_FOUND)
if ((AVX512_FOUND AND NOT AVX512_DISABLED) OR ASIMD_FOUND OR POWER9_FOUND OR POWER10_FOUND OR POWER11_FOUND)
FetchContent_Declare(
oneDNN
GIT_REPOSITORY https://github.com/oneapi-src/oneDNN.git
GIT_TAG v3.8.1
GIT_TAG v3.9
GIT_PROGRESS TRUE
GIT_SHALLOW TRUE
)
@@ -204,7 +204,7 @@ if ((AVX512_FOUND AND NOT AVX512_DISABLED) OR ASIMD_FOUND)
endif()
set(ONEDNN_AARCH64_USE_ACL "ON")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wl,-rpath,$ENV{ACL_ROOT_DIR}/build/")
endif()
endif()
set(ONEDNN_LIBRARY_TYPE "STATIC")
set(ONEDNN_BUILD_DOC "OFF")
@@ -217,38 +217,23 @@ if ((AVX512_FOUND AND NOT AVX512_DISABLED) OR ASIMD_FOUND)
set(ONEDNN_ENABLE_ITT_TASKS "OFF")
set(ONEDNN_ENABLE_MAX_CPU_ISA "OFF")
set(ONEDNN_ENABLE_CPU_ISA_HINTS "OFF")
set(ONEDNN_VERBOSE "OFF")
set(CMAKE_POLICY_DEFAULT_CMP0077 NEW)
FetchContent_MakeAvailable(oneDNN)
list(APPEND LIBS dnnl)
elseif(POWER10_FOUND)
FetchContent_Declare(
oneDNN
GIT_REPOSITORY https://github.com/oneapi-src/oneDNN.git
GIT_TAG v3.7.2
GIT_PROGRESS TRUE
GIT_SHALLOW TRUE
add_library(dnnl_ext OBJECT "csrc/cpu/dnnl_helper.cpp")
target_include_directories(
dnnl_ext
PUBLIC ${oneDNN_SOURCE_DIR}/include
PUBLIC ${oneDNN_BINARY_DIR}/include
PRIVATE ${oneDNN_SOURCE_DIR}/src
)
set(ONEDNN_LIBRARY_TYPE "STATIC")
set(ONEDNN_BUILD_DOC "OFF")
set(ONEDNN_BUILD_EXAMPLES "OFF")
set(ONEDNN_BUILD_TESTS "OFF")
set(ONEDNN_ENABLE_WORKLOAD "INFERENCE")
set(ONEDNN_ENABLE_PRIMITIVE "MATMUL;REORDER")
set(ONEDNN_BUILD_GRAPH "OFF")
set(ONEDNN_ENABLE_JIT_PROFILING "OFF")
set(ONEDNN_ENABLE_ITT_TASKS "OFF")
set(ONEDNN_ENABLE_MAX_CPU_ISA "OFF")
set(ONEDNN_ENABLE_CPU_ISA_HINTS "OFF")
set(CMAKE_POLICY_DEFAULT_CMP0077 NEW)
set(DNNL_CPU_RUNTIME "OMP")
FetchContent_MakeAvailable(oneDNN)
list(APPEND LIBS dnnl)
target_link_libraries(dnnl_ext dnnl)
target_compile_options(dnnl_ext PRIVATE ${CXX_COMPILE_FLAGS} -fPIC)
list(APPEND LIBS dnnl_ext)
set(USE_ONEDNN ON)
else()
set(USE_ONEDNN OFF)
endif()
message(STATUS "CPU extension compile flags: ${CXX_COMPILE_FLAGS}")
@@ -275,7 +260,6 @@ set(VLLM_EXT_SRC
if (AVX512_FOUND AND NOT AVX512_DISABLED)
set(VLLM_EXT_SRC
"csrc/cpu/quant.cpp"
"csrc/cpu/shm.cpp"
${VLLM_EXT_SRC})
if (ENABLE_AVX512BF16 AND ENABLE_AVX512VNNI)
@@ -289,14 +273,11 @@ if (AVX512_FOUND AND NOT AVX512_DISABLED)
${VLLM_EXT_SRC})
add_compile_definitions(-DCPU_CAPABILITY_AVX512)
endif()
elseif(POWER10_FOUND)
set(VLLM_EXT_SRC
"csrc/cpu/quant.cpp"
${VLLM_EXT_SRC})
endif()
if (ASIMD_FOUND)
if(USE_ONEDNN)
set(VLLM_EXT_SRC
"csrc/cpu/quant.cpp"
"csrc/cpu/dnnl_kernels.cpp"
${VLLM_EXT_SRC})
endif()