Dockerfile

# ╔══════════════════════════════════════════════════════════════╗
# ║   Granite 4.0 ONNX Inference Server                         ║
# ║   Model: onnx-community/granite-4.0-h-350m-ONNX             ║
# ║   Runtime: ONNX Runtime CPU · FastAPI · Beautiful UI         ║
# ╚══════════════════════════════════════════════════════════════╝

FROM python:3.11-slim

# ── System dependencies ───────────────────────────────────────────────────────
RUN apt-get update && apt-get install -y \
    git \
    curl \
    build-essential \
    && rm -rf /var/lib/apt/lists/*

# ── Create non-root user (HuggingFace Spaces requirement) ─────────────────────
RUN useradd -m -u 1000 user
USER user

ENV HOME=/home/user \
    PATH=/home/user/.local/bin:$PATH \
    HF_HOME=/home/user/.cache/huggingface \
    TRANSFORMERS_CACHE=/home/user/.cache/huggingface \
    # Prevents OMP issues on CPU
    OMP_NUM_THREADS=4 \
    MKL_NUM_THREADS=4

WORKDIR /app

# ── Install Python dependencies ───────────────────────────────────────────────
COPY --chown=user requirements.txt .
RUN pip install --no-cache-dir --upgrade pip && \
    pip install --no-cache-dir -r requirements.txt

# ── Copy application files ────────────────────────────────────────────────────
COPY --chown=user server.py .
COPY --chown=user static/ ./static/

# ── Expose port (HF Spaces uses 7860) ────────────────────────────────────────
EXPOSE 7860

# ── Health check ─────────────────────────────────────────────────────────────
HEALTHCHECK --interval=30s --timeout=10s --start-period=120s --retries=3 \
    CMD curl -f http://localhost:7860/health || exit 1

# ── Launch server ─────────────────────────────────────────────────────────────
CMD ["uvicorn", "server:app", \
     "--host", "0.0.0.0", \
     "--port", "7860", \
     "--workers", "1", \
     "--log-level", "info"]