Mirrors
/
hf_text-generation-inference
mirror of https://github.com/huggingface/text-generation-inference.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

fix: set cuda arch list prior to vllm build

This commit is contained in:
drbh 2024-05-27 09:00:34 -04:00
parent ad94f299f4
commit da1a0b3412
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
.github/workflows/python-packaging.yaml vendored
View File

@ -164,6 +164,7 @@ jobs:
git clone https://github.com/Narsil/vllm.git
cd vllm
git checkout b5dfc61db88a81069e45b44f7cc99bd9e62a60fa
export TORCH_CUDA_ARCH_LIST="8.0 8.6 8.9 9.0"
python setup.py bdist_wheel --dist-dir=../dist
# Generate a custom name for the wheel to include CUDA and Torch versions
tmpname=cu${MATRIX_CUDA_VERSION}torch${MATRIX_TORCH_VERSION}cxx11abi${{ matrix.cxx11_abi }}