owen/worker-vllm
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update Dockerfile

Browse Source
This commit is contained in:
Justin Merrell
2023-12-08 20:23:23 -05:00
parent 4052a17af1
commit 35a74475f2
1 changed files with 7 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Dockerfile
+7 -6
View File
@@ -17,9 +17,9 @@ RUN --mount=type=cache,target=/root/.cache/pip \
# Install specific packages based on CUDA version
RUN if [ "$CUDA_VERSION" == "12.1.0" ]; then \
python3.11 -m pip install vllm==0.2.3; \
python3.11 -m pip install vllm==0.2.3; \
else \
python3.11 -m pip install https://github.com/vllm-project/vllm/releases/download/v0.2.3/vllm-0.2.3+cu118-cp311-cp311-manylinux1_x86_64.whl; \
python3.11 -m pip install https://github.com/vllm-project/vllm/releases/download/v0.2.3/vllm-0.2.3+cu118-cp311-cp311-manylinux1_x86_64.whl; \
fi
@@ -28,13 +28,14 @@ ADD src .
ARG MODEL_NAME=""
ARG MODEL_BASE_PATH=""
ARG HUGGING_FACE_HUB_TOKEN=""
# Conditionally run download_model.py
RUN if [ -n "$MODEL_NAME" ] && [ -n "$MODEL_BASE_PATH" ]; then \
python3.11 /download_model.py --model $MODEL_NAME --download_dir $MODEL_BASE_PATH; \
export MODEL_NAME=$MODEL_NAME; \
export MODEL_BASE_PATH=$MODEL_BASE_PATH; \
python3.11 /download_model.py --model $MODEL_NAME --download_dir $MODEL_BASE_PATH; \
export MODEL_NAME=$MODEL_NAME; \
export MODEL_BASE_PATH=$MODEL_BASE_PATH; \
fi
# Start the handler
CMD ["python3.11", "/handler.py"]
CMD ["python3.11", "/handler.py"]