File size: 429 Bytes
4a28d4d | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 | ARG CUDA_VERSION=cu12
FROM openmmlab/lmdeploy:latest-cu12 AS cu12
ENV CUDA_VERSION_SHORT=cu123
FROM openmmlab/lmdeploy:latest-cu11 AS cu11
ENV CUDA_VERSION_SHORT=cu118
FROM ${CUDA_VERSION} AS final
RUN python3 -m pip install timm!=1.0.23
RUN python3 -m pip install https://github.com/Dao-AILab/flash-attention/releases/download/v2.6.3/flash_attn-2.6.3+${CUDA_VERSION_SHORT}torch2.3cxx11abiFALSE-cp310-cp310-linux_x86_64.whl
|