20231088/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Disable GPTQ AllSpark kernels for CUDA Compiler < 12.0 (#14157)

Browse Source 
Signed-off-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
Michael Goin 2025-03-04 23:25:24 -05:00 committed by GitHub
parent 5b143d33be
commit e123aafdf0
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
CMakeLists.txt
View File

@ -319,7 +319,7 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
# Only build AllSpark kernels if we are building for at least some compatible archs.
cuda_archs_loose_intersection(ALLSPARK_ARCHS "8.0;8.6;8.7;8.9" "${CUDA_ARCHS}")
if (ALLSPARK_ARCHS)
if (${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER 12.0 AND ALLSPARK_ARCHS)
set(ALLSPARK_SRCS
"csrc/quantization/gptq_allspark/allspark_repack.cu"
"csrc/quantization/gptq_allspark/allspark_qgemm_w8a16.cu")
@ -330,7 +330,7 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
message(STATUS "Building AllSpark kernels for archs: ${ALLSPARK_ARCHS}")
else()
message(STATUS "Not building AllSpark kernels as no compatible archs found"
" in CUDA target architectures")
" in CUDA target architectures, or CUDA not >= 12.0")
endif()
# The cutlass_scaled_mm kernels for Hopper (c3x, i.e. CUTLASS 3.x) require