amd-r9700-vllm-toolboxes/Dockerfile

FROM docker.1ms.run/kyuz0/vllm-therock-gfx1201:latest

# Set environment variables
ENV USE_DEFAULT_MODEL=true
ENV LOCAL_MODEL_DIR=/opt/model

# Create necessary directories
RUN mkdir -p /opt/script /opt/model /config

# Copy scripts to /opt/script
COPY scripts/add_qwen3_5_moe_support.py /opt/script/add_qwen3_5_moe_support.py
COPY scripts/start_vllm.py /opt/script/start-vllm
COPY benchmarks/run_vllm_bench.py /opt/script/run_vllm_bench.py

# Update vLLM to nightly version for Qwen3.5 support
RUN pip install --upgrade vllm --extra-index-url https://wheels.vllm.ai/nightly

# Add qwen3_5_moe support to Transformers
RUN python3 /opt/script/add_qwen3_5_moe_support.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"]