Dockerfile.hpc

# Use NVIDIA CUDA base image
FROM nvidia/cuda:11.8.0-devel-ubuntu22.04

# Set environment variables
ENV PYTHONUNBUFFERED=1 \
    PYTHONDONTWRITEBYTECODE=1 \
    PIP_NO_CACHE_DIR=1 \
    NVIDIA_VISIBLE_DEVICES=all \
    DEBIAN_FRONTEND=noninteractive

# Install system dependencies
RUN apt-get update && apt-get install -y \
    python3.10 \
    python3.10-dev \
    python3-pip \
    build-essential \
    curl \
    git \
    libssl-dev \
    && rm -rf /var/lib/apt/lists/*

# Set working directory
WORKDIR /app

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

# Install HPC and ML dependencies
RUN pip3 install --no-cache-dir \
    torch \
    torchvision \
    torchaudio \
    cupy-cuda11x \
    horovod \
    mpi4py \
    dask \
    dask-cuda \
    ray[default] \
    ray[serve]

# Copy application code
COPY hpc /app/hpc
COPY config /app/config

# Set Python path
ENV PYTHONPATH=/app

# Add health check
HEALTHCHECK --interval=30s --timeout=30s --start-period=5s --retries=3 \
    CMD curl -f http://localhost:8001/health || exit 1

# Command to run the application
CMD ["python3", "-m", "hpc.orchestrator"]