obscura/vllm
2
0
Fork 0
mirror of https://github.com/vllm-project/vllm.git synced 2026-06-06 00:16:14 +00:00
Code Issues Packages Projects Releases Wiki Activity

[Bugfix] Install nvidia-cutlass-dsl[cu13] extra on CUDA 13 platforms (#42438)

Browse Source 
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
This commit is contained in:
Jiangyun Zhu
2026-05-13 16:57:21 +08:00
committed by GitHub
parent 9ce74042d3
commit 140dc2ec30
4 changed files with 14 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
setup.py
+3
View File
@@ -970,6 +970,9 @@ def get_requirements() -> list[str]:
# vllm-flash-attn is built only for CUDA 12.x.
# Skip for other versions.
continue
if "nvidia-cutlass-dsl[cu13]" in req and cuda_major == "12":
# [cu13] extra is the default; strip it on CUDA 12 builds.
req = req.replace("nvidia-cutlass-dsl[cu13]", "nvidia-cutlass-dsl")
modified_requirements.append(req)
requirements = modified_requirements
elif _is_hip():