Dockerfile

FROM nvidia/cuda:12.1.0-runtime-ubuntu22.04

# Set working directory
WORKDIR /app

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

# Create symlink for python
RUN ln -s /usr/bin/python3.11 /usr/bin/python

# Copy requirements first for better caching
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Copy application code
COPY . .

# Set environment variables
ENV PYTHONUNBUFFERED=1
ENV TOKENIZERS_PARALLELISM=false
ENV CUDA_VISIBLE_DEVICES=0

# Expose ports
EXPOSE 8000 8001

# Default command (can be overridden)
CMD ["python", "-m", "agent.model_server"]