# Base image: torch 2.8.0+cu128 still lists sm_70 in torch.cuda.get_arch_list().
# The CUDA 13 builds of torch drop sm_70. worker-1 holds Tesla V100 cards with
# compute capability 7.0, so a newer base kills the kernel launch at load time.
# Keep this pin until the model moves to newer hardware.
FROM pytorch/pytorch:2.8.0-cuda12.8-cudnn9-runtime

# Unbuffered output lets the pod log show the startup lines in order.
ENV PYTHONUNBUFFERED=1 \
    PIP_NO_CACHE_DIR=1

WORKDIR /app

# torch comes from the base image. Never reinstall it here, or pip pulls a
# wheel built for another CUDA version.
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

COPY app.py .

EXPOSE 8080

CMD ["uvicorn", "app:create_app", "--factory", "--host", "0.0.0.0", "--port", "8080"]