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:
Alpay Ariyak
2023-12-19 00:58:45 -05:00
committed by GitHub
parent 8a11a7e4ed
commit c321d828ab
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Dockerfile
+3 -3
View File
@@ -21,10 +21,10 @@ RUN --mount=type=cache,target=/root/.cache/pip \
# Install torch and vllm based on CUDA version
RUN if [[ "${WORKER_CUDA_VERSION}" == 11.8* ]]; then \
python3.11 -m pip install -e git+https://github.com/alpayariyak/vllm.git@cuda-11.8#egg=vllm; \
python3.11 -m pip install -e git+https://github.com/runpod/vllm-fork-for-sls-worker.git@cuda-11.8#egg=vllm; \
python3.11 -m pip install -U --force-reinstall torch==2.1.2 xformers==0.0.23.post1 --index-url https://download.pytorch.org/whl/cu118; \
else \
python3.11 -m pip install -e git+https://github.com/alpayariyak/vllm.git#egg=vllm; \
python3.11 -m pip install -e git+https://github.com/runpod/vllm-fork-for-sls-worker.git#egg=vllm; \
fi && \
rm -rf /root/.cache/pip
@@ -47,4 +47,4 @@ RUN if [ -n "$MODEL_NAME" ]; then \
fi
# Start the handler
CMD ["python3.11", "/handler.py"]
CMD ["python3.11", "/handler.py"]