install flash attention in 2.9.0 base images (#3224)

This commit is contained in:
Wing Lian
2025-10-22 21:24:52 -07:00
committed by GitHub
parent 4dc018992d
commit bb33fda44d
2 changed files with 10 additions and 2 deletions

View File

@@ -34,3 +34,9 @@ RUN uv pip install packaging setuptools wheel psutil \
&& uv pip install --no-build-isolation "causal_conv1d @ git+https://github.com/Dao-AILab/causal-conv1d.git@main" \
&& uv pip install "mamba_ssm @ git+https://github.com/state-spaces/mamba.git@main" \
&& uv pip install awscli pydantic
RUN if [ "$PYTORCH_VERSION" = "2.9.0" ] && [ "$CUDA" = "128" ] ; then \
wget https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/v0.4.17/flash_attn-2.8.3+cu128torch2.9-cp311-cp311-linux_x86_64.whl; \
uv pip install --no-cache-dir flash_attn-2.8.3+cu128torch2.9-cp311-cp311-linux_x86_64.whl; \
rm flash_attn-2.8.3+cu128torch2.9-cp311-cp311-linux_x86_64.whl; \
fi