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:
Marut Pandya
2025-05-09 09:27:54 -07:00
committed by GitHub
parent 9b7ca4d0b0
commit 6db2c44d3b
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Dockerfile
+2 -2
View File
@@ -12,7 +12,7 @@ RUN --mount=type=cache,target=/root/.cache/pip \
python3 -m pip install --upgrade -r /requirements.txt python3 -m pip install --upgrade -r /requirements.txt
# Install vLLM (switching back to pip installs since issues that required building fork are fixed and space optimization is not as important since caching) and FlashInfer # Install vLLM (switching back to pip installs since issues that required building fork are fixed and space optimization is not as important since caching) and FlashInfer
RUN python3 -m pip install vllm==0.8.4 && \ RUN python3 -m pip install vllm==0.8.5 && \
python3 -m pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.3 python3 -m pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.3
# Setup for Option 2: Building the Image with the Model included # Setup for Option 2: Building the Image with the Model included
@@ -47,4 +47,4 @@ RUN --mount=type=secret,id=HF_TOKEN,required=false \
fi fi
# Start the handler # Start the handler
CMD ["python3", "/src/handler.py"] CMD ["python3", "/src/handler.py"]