biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Kernel] Integrate SM100 MXFP8 blockscaled grouped MM and quant kernels (#34448)

Browse Source 
Signed-off-by: EdalatiAli <aliedalati@cohere.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
This commit is contained in:
EdalatiAli
2026-03-02 02:31:19 -05:00
committed by GitHub
parent c34963f138
commit cb21972a97
10 changed files with 1331 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
CMakeLists.txt
View File

@@ -771,6 +771,33 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
endif()
endif()
# Expert-specialization MXFP8 blockscaled grouped kernels (SM100+).
if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 13.0)
cuda_archs_loose_intersection(ES_MXFP8_GROUPED_MM_ARCHS "10.0f;11.0f" "${CUDA_ARCHS}")
else()
cuda_archs_loose_intersection(ES_MXFP8_GROUPED_MM_ARCHS "10.0a;10.1a;10.3a" "${CUDA_ARCHS}")
endif()
if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 12.8 AND ES_MXFP8_GROUPED_MM_ARCHS)
set(SRCS
"csrc/moe/mxfp8_moe/cutlass_mxfp8_grouped_mm.cu"
"csrc/moe/mxfp8_moe/mxfp8_experts_quant.cu")
set_gencode_flags_for_srcs(
SRCS "${SRCS}"
CUDA_ARCHS "${ES_MXFP8_GROUPED_MM_ARCHS}")
list(APPEND VLLM_EXT_SRC "${SRCS}")
list(APPEND VLLM_GPU_FLAGS "-DENABLE_ES_MXFP8_GROUPED_MM_SM100=1")
message(STATUS "Building ES MXFP8 grouped kernels for archs: ${ES_MXFP8_GROUPED_MM_ARCHS}")
else()
if (NOT ${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 12.8
AND ES_MXFP8_GROUPED_MM_ARCHS)
message(STATUS "Not building ES MXFP8 grouped kernels as CUDA Compiler version is "
"not >= 12.8.")
else()
message(STATUS "Not building ES MXFP8 grouped kernels as no compatible archs found "
"in CUDA target architectures.")
endif()
endif()
# DeepSeek V3 fused A GEMM kernel (requires SM 9.0+, Hopper and later)
if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 13.0)
cuda_archs_loose_intersection(DSV3_FUSED_A_GEMM_ARCHS "9.0a;10.0f;11.0f" "${CUDA_ARCHS}")