FROM nvidia/cuda:12.4.0-runtime-ubuntu22.04

WORKDIR /app

# Install Python and system dependencies
RUN apt-get update && apt-get install -y \
    python3.11 \
    python3-pip \
    git \
    && rm -rf /var/lib/apt/lists/*

# Upgrade pip
RUN pip3 install --no-cache-dir --upgrade pip

# Install vLLM and dependencies
COPY requirements.txt .
RUN pip3 install --no-cache-dir -r requirements.txt

# Copy application code
COPY server.py .

# Create directory for model cache
RUN mkdir -p /workspace/huggingface_cache

# Environment variables
ENV HF_HOME=/workspace/huggingface_cache
ENV VLLM_HOST=0.0.0.0
ENV VLLM_PORT=8000

# Expose port
EXPOSE 8000

# Run the server
CMD ["python3", "server.py"]