Skip to content

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

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jun 9, 2025
Merged

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

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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
# are not supported by Machete yet.
# 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)

#
Expand Down Expand Up @@ -454,7 +454,7 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
# kernels for the remaining archs that are not already built for 3x.
# (Build 8.9 for FP8)
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
list(REMOVE_ITEM SCALED_MM_2X_ARCHS ${SCALED_MM_3X_ARCHS})
if (SCALED_MM_2X_ARCHS)
Expand Down Expand Up @@ -684,7 +684,7 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")

list(APPEND VLLM_MOE_EXT_SRC "${VLLM_MOE_WNA16_SRC}")
# 9.0 for latest bf16 atomicAdd PTX
cuda_archs_loose_intersection(MARLIN_MOE_ARCHS "8.0;9.0+PTX" "${CUDA_ARCHS}")
cuda_archs_loose_intersection(MARLIN_MOE_ARCHS "8.0;8.7;9.0+PTX" "${CUDA_ARCHS}")
if (MARLIN_MOE_ARCHS)

#
Expand Down