Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 6 additions & 1 deletion deploy/Dockerfile
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,11 @@ ENV TORCH_CUDA_ARCH_LIST "7.0;7.2;7.5;8.0;8.6;8.9;9.0"
RUN pip3 install "torch==2.1.1"

# This build is slow but NVIDIA does not provide binaries. Increase MAX_JOBS as needed.
# MAX_JOBS needs to be passed into the container by ENV but is defined before as ARG to
# make it possible to configure it at build time with "--build-arg MAX_JOBS=x".
ARG MAX_JOBS
ENV MAX_JOBS=$MAX_JOBS

RUN pip3 install "git+https://github.com/stanford-futuredata/megablocks.git"
RUN pip3 install "git+https://github.com/vllm-project/vllm.git"
RUN pip3 install "xformers==0.0.23" "transformers==4.36.0" "fschat[model_worker]==0.2.34"
Expand All @@ -28,4 +33,4 @@ COPY entrypoint.sh .

RUN chmod +x /workspace/entrypoint.sh

ENTRYPOINT ["/workspace/entrypoint.sh"]
ENTRYPOINT ["/workspace/entrypoint.sh"]