30 lines
865 B
Docker
30 lines
865 B
Docker
FROM docker.1ms.run/kyuz0/vllm-therock-gfx1201:latest
|
|
|
|
# Set environment variables
|
|
ENV USE_DEFAULT_MODEL=true
|
|
ENV LOCAL_MODEL_DIR=/opt/model
|
|
|
|
# Ensure latest Transformers model definitions are available
|
|
RUN /opt/venv/bin/pip install --no-cache-dir --upgrade "git+https://github.com/huggingface/transformers.git"
|
|
|
|
# Create necessary directories
|
|
RUN mkdir -p /opt/script /opt/model /config
|
|
|
|
# Copy scripts to /opt/script
|
|
COPY scripts/start_vllm.py /opt/script/start-vllm
|
|
COPY benchmarks/run_vllm_bench.py /opt/script/run_vllm_bench.py
|
|
|
|
# Note: config.json should be mounted at runtime via docker-compose.yml
|
|
|
|
# Make scripts executable
|
|
RUN chmod +x /opt/script/start-vllm
|
|
|
|
# Replace the container's start-vllm with our improved version
|
|
RUN cp /opt/script/start-vllm /usr/local/bin/start-vllm
|
|
|
|
# Set working directory
|
|
WORKDIR /opt
|
|
|
|
# Default command
|
|
CMD ["start-vllm"]
|