saif-4b / serving /Dockerfile
GyrTech's picture
Add CPU-verified decision-only serving kit and container usage
73bc533 verified
Raw History Blame Contribute Delete
620 Bytes
FROM pytorch/pytorch:2.8.0-cuda12.8-cudnn9-runtime
WORKDIR /app
COPY requirements.txt .
RUN python -m pip uninstall -y torchao && python -m pip install --no-cache-dir -r requirements.txt
RUN useradd --create-home --uid 10001 saif
COPY serve.py run.py ./
USER saif
ENV SAIF_DEVICE=cpu SAIF_THREADS=4 PORT=8000 HF_HOME=/home/saif/.cache/huggingface PYTHONDONTWRITEBYTECODE=1
EXPOSE 8000
HEALTHCHECK --interval=30s --timeout=5s --start-period=180s --retries=3 CMD python -c "import os,urllib.request; urllib.request.urlopen('http://127.0.0.1:'+os.environ.get('PORT','8000')+'/health',timeout=4)"
CMD ["python", "serve.py"]