Dockerfile

FROM nvidia/cuda:12.1.0-devel-ubuntu22.04 AS dev

RUN apt-get update -y \
    && apt-get install -y python3-pip git

# Workaround for https://github.com/openai/triton/issues/2507 and
# https://github.com/pytorch/pytorch/issues/107960 -- hopefully
# this won't be needed for future versions of this docker image
# or future versions of triton.
RUN ldconfig /usr/local/cuda-12.1/compat/
RUN pip install cmake>=3.21 ninja psutil sentencepiece numpy requests py-cpuinfo transformers >= 4.39.1  fastapi uvicorn[standard] pydantic >= 2.0 prometheus_client >= 0.18.0 tiktoken == 0.6.0 outlines == 0.0.34 
RUN ray >= 2.9 pynvml==11.5.0 vllm-nccl-cu12>=2.18,<2.19  torch==2.2.1 xformers == 0.0.25 triton>=2.1.0

WORKDIR /code

COPY ./requirements.txt /code/requirements.txt

# Set up a new user named "user" with user ID 1000
RUN useradd -m -u 1000 user
# Switch to the "user" user
USER user
# Set home to the user's home directory
ENV HOME=/home/user \
	PATH=/home/user/.local/bin:$PATH \
    PYTHONPATH=$HOME/app \
	PYTHONUNBUFFERED=1 \
	GRADIO_ALLOW_FLAGGING=never \
	GRADIO_NUM_PORTS=1 \
	GRADIO_SERVER_NAME=0.0.0.0 \
	GRADIO_THEME=huggingface \
	SYSTEM=spaces

RUN pip3 install --no-cache-dir --upgrade -r /code/requirements.txt

# Set the working directory to the user's home directory
WORKDIR $HOME/app

# Copy the current directory contents into the container at $HOME/app setting the owner to the user
COPY --chown=user . $HOME/app

CMD ["python3", "app.py"]