Quantization-Attempts / Dockerfile
Rúben Almeida
Revert to use CPU resources in the quantization process
1a1e448
raw
history blame
799 Bytes
FROM python:3.13-slim
RUN apt-get update && apt-get install -y build-essential
RUN useradd -m -u 1000 user
USER user
ENV HOME=/home/user \
PATH=/home/user/.local/bin:$PATH
# Set the working directory
WORKDIR $HOME/app
# Update pip to the latest version
RUN pip install --upgrade pip
RUN pip install -U setuptools wheel
# Install torch cpu version
RUN pip install -U torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cpu
# Copy the requirements file into the container
COPY --chown=user requirements.txt .
# Install the dependencies
RUN pip install -U --no-cache-dir -r requirements.txt
# Copy the rest of the application code into the container
COPY --chown=user . .
EXPOSE 7860
ENTRYPOINT ["fastapi", "run", "main.py", "--host=0.0.0.0", "--port=7860"]