[Refactor] Remove dead cutlass mxfp8 code (#44681)

Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Shengqi Chen <harry-chen@outlook.com>
This commit is contained in:
Wentao Ye
2026-06-17 21:18:25 -07:00
committed by GitHub
co-authored by Shengqi Chen
parent f428718ffe
commit b4c80ec0fd
10 changed files with 0 additions and 1369 deletions
-29
View File
@@ -363,35 +363,6 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
SRCS "${VLLM_EXT_SRC}"
CUDA_ARCHS "${CUDA_ARCHS}")
# 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(ES_MXFP8_GROUPED_MM_SRCS
"csrc/libtorch_stable/moe/mxfp8_moe/cutlass_mxfp8_grouped_mm.cu"
"csrc/libtorch_stable/moe/mxfp8_moe/mxfp8_experts_quant.cu")
set_gencode_flags_for_srcs(
SRCS "${ES_MXFP8_GROUPED_MM_SRCS}"
CUDA_ARCHS "${ES_MXFP8_GROUPED_MM_ARCHS}")
list(APPEND VLLM_STABLE_EXT_SRC "${ES_MXFP8_GROUPED_MM_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()
# if CUDA endif
endif()