bump flash-attn to 2.0.4 for the base docker image (#382)

This commit is contained in:
Wing Lian
2023-08-13 17:55:04 -04:00
committed by GitHub
parent 15f6e57eaa
commit ffac902c1b

View File

@@ -40,7 +40,7 @@ ARG TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6 9.0+PTX"
RUN git clone https://github.com/Dao-AILab/flash-attention.git && \
cd flash-attention && \
git checkout v2.0.1 && \
git checkout v2.0.4 && \
python3 setup.py bdist_wheel && \
cd csrc/fused_dense_lib && \
python3 setup.py bdist_wheel && \