biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[CI Bugfix] Specify same TORCH_CUDA_ARCH_LIST for flashinfer aot and install (#20772)

Browse Source 
Signed-off-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
Michael Goin
2025-07-11 10:16:01 +09:00
committed by GitHub
parent b854321ffe
commit cf75cd2098
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
docker/Dockerfile
View File

@@ -408,6 +408,7 @@ RUN --mount=type=cache,target=/root/.cache/uv bash - <<'BASH'
# Needed to build AOT kernels # Needed to build AOT kernels
pushd flashinfer pushd flashinfer
TORCH_CUDA_ARCH_LIST="${FI_TORCH_CUDA_ARCH_LIST}" \
python3 -m flashinfer.aot python3 -m flashinfer.aot
TORCH_CUDA_ARCH_LIST="${FI_TORCH_CUDA_ARCH_LIST}" \ TORCH_CUDA_ARCH_LIST="${FI_TORCH_CUDA_ARCH_LIST}" \
uv pip install --system --no-build-isolation . uv pip install --system --no-build-isolation .