xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-03-16 14:17:16 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bugfix] Adjust Marlin CUDA arch selection to 8.0+PTX;9.0+PTX (#28294)

Browse Source
This commit is contained in:
Michael Goin 2025-11-12 18:14:13 -05:00 committed by GitHub
parent 3eb0c2673e
commit 10f01d5a3a
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

@ -331,7 +331,7 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
# Keep building Marlin for 9.0 as there are some group sizes and shapes that # Keep building Marlin for 9.0 as there are some group sizes and shapes that
# are not supported by Machete yet. # are not supported by Machete yet.
# 9.0 for latest bf16 atomicAdd PTX # 9.0 for latest bf16 atomicAdd PTX
cuda_archs_loose_intersection(MARLIN_ARCHS "8.0;8.7;9.0+PTX" "${CUDA_ARCHS}") cuda_archs_loose_intersection(MARLIN_ARCHS "8.0+PTX;9.0+PTX" "${CUDA_ARCHS}")
if (MARLIN_ARCHS) if (MARLIN_ARCHS)
# #
@ -915,7 +915,7 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
list(APPEND VLLM_MOE_EXT_SRC "${VLLM_MOE_WNA16_SRC}") list(APPEND VLLM_MOE_EXT_SRC "${VLLM_MOE_WNA16_SRC}")
# 9.0 for latest bf16 atomicAdd PTX # 9.0 for latest bf16 atomicAdd PTX
cuda_archs_loose_intersection(MARLIN_MOE_ARCHS "8.0;8.7;9.0+PTX" "${CUDA_ARCHS}") cuda_archs_loose_intersection(MARLIN_MOE_ARCHS "8.0+PTX;9.0+PTX" "${CUDA_ARCHS}")
if (MARLIN_MOE_ARCHS) if (MARLIN_MOE_ARCHS)
# #