xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-09 20:04:27 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Build] Revert triton_kernels requirements (#27659)

Browse Source
This commit is contained in:
Varun Sundar Rabindranath 2025-10-29 00:07:09 -04:00 committed by GitHub
parent 9007bf57e6
commit f6d5f5888c
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 0 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
requirements/cuda.txt
View File

@ -13,5 +13,3 @@ torchvision==0.24.0 # Required for phi3v processor. See https://github.com/pytor
# xformers==0.0.32.post1; platform_system == 'Linux' and platform_machine == 'x86_64' # Requires PyTorch >= 2.8
# FlashInfer should be updated together with the Dockerfile
flashinfer-python==0.4.1
# Triton Kernels are needed for mxfp4 fused moe. (Should be updated alongside torch)
triton_kernels @ git+https://github.com/triton-lang/triton.git@v3.5.0#subdirectory=python/triton_kernels