xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-05-21 10:26:59 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Fix] Allow kernel compilation for CUDA capability 8.7 (#19328)

Browse Source 
Signed-off-by: Conroy Cheers <conroy@corncheese.org>
This commit is contained in:
Conroy Cheers 2025-06-09 19:57:23 +10:00 committed by GitHub
parent 95a6568b5c
commit 59abbd84f9
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
CMakeLists.txt
View File

@ -308,7 +308,7 @@ 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;9.0+PTX" "${CUDA_ARCHS}") cuda_archs_loose_intersection(MARLIN_ARCHS "8.0;8.7;9.0+PTX" "${CUDA_ARCHS}")
if (MARLIN_ARCHS) if (MARLIN_ARCHS)
# #
@ -454,7 +454,7 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
# kernels for the remaining archs that are not already built for 3x. # kernels for the remaining archs that are not already built for 3x.
# (Build 8.9 for FP8) # (Build 8.9 for FP8)
cuda_archs_loose_intersection(SCALED_MM_2X_ARCHS cuda_archs_loose_intersection(SCALED_MM_2X_ARCHS
"7.5;8.0;8.9+PTX" "${CUDA_ARCHS}") "7.5;8.0;8.7;8.9+PTX" "${CUDA_ARCHS}")
# subtract out the archs that are already built for 3x # subtract out the archs that are already built for 3x
list(REMOVE_ITEM SCALED_MM_2X_ARCHS ${SCALED_MM_3X_ARCHS}) list(REMOVE_ITEM SCALED_MM_2X_ARCHS ${SCALED_MM_3X_ARCHS})
if (SCALED_MM_2X_ARCHS) if (SCALED_MM_2X_ARCHS)
@ -684,7 +684,7 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
list(APPEND VLLM_MOE_EXT_SRC "${VLLM_MOE_WNA16_SRC}") list(APPEND VLLM_MOE_EXT_SRC "${VLLM_MOE_WNA16_SRC}")
# 9.0 for latest bf16 atomicAdd PTX # 9.0 for latest bf16 atomicAdd PTX
cuda_archs_loose_intersection(MARLIN_MOE_ARCHS "8.0;9.0+PTX" "${CUDA_ARCHS}") cuda_archs_loose_intersection(MARLIN_MOE_ARCHS "8.0;8.7;9.0+PTX" "${CUDA_ARCHS}")
if (MARLIN_MOE_ARCHS) if (MARLIN_MOE_ARCHS)
# #