Dockerfile

FROM nvidia/cuda:12.1.1-cudnn8-runtime-ubuntu22.04

ENV DEBIAN_FRONTEND=noninteractive \
    PYTHONUNBUFFERED=1 \
    PYTHONDONTWRITEBYTECODE=1

RUN apt-get update && apt-get install -y --no-install-recommends \
    software-properties-common \
    curl \
    git \
    && add-apt-repository ppa:deadsnakes/ppa \
    && apt-get update && apt-get install -y --no-install-recommends \
    python3.12 \
    python3.12-dev \
    python3.12-venv \
    && rm -rf /var/lib/apt/lists/*

# uv
COPY --from=ghcr.io/astral-sh/uv:latest /uv /usr/local/bin/uv

WORKDIR /app

# Install dependencies first (better layer caching — only reruns when lock file changes)
COPY pyproject.toml uv.lock .python-version ./
RUN uv sync --no-dev --no-install-project --extra-index-url https://download.pytorch.org/whl/cu121

# Copy source after deps so code changes don't invalidate the dep layer
COPY src/ src/
COPY configs/ configs/

# Make the src package importable without building a wheel
ENV PYTHONPATH=/app/src

# HuggingFace cache mount point
VOLUME ["/root/.cache/huggingface"]

# Output mount point
VOLUME ["/app/output"]

CMD ["uv", "run", "sft-train", "configs/prod.yaml"]