Spaces:
Paused
Paused
File size: 1,720 Bytes
22d91a3 6a1e76c 175eaf8 d42a4e0 175eaf8 eab0ed4 6808494 175eaf8 22d91a3 41adfc5 e60e653 eab0ed4 e60e653 e305cfe 45cedd9 2abee9d f482f96 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 |
# syntax=docker/dockerfile:1
# Build as `docker build . -t localgpt`, requires BuildKit.
# Run as `docker run -it --mount src="$HOME/.cache",target=/root/.cache,type=bind --gpus=all localgpt`, requires Nvidia container toolkit.
FROM nvidia/cuda:12.1.1-devel-ubuntu22.04
ENV HOST 0.0.0.0
RUN apt-get update && apt-get upgrade -y \
&& apt-get install -y git build-essential libpq-dev gcc \
wget ocl-icd-opencl-dev opencl-headers clinfo \
libclblast-dev libopenblas-dev software-properties-common\
g++-11 make python3 python-is-python3 pip \
&& mkdir -p /etc/OpenCL/vendors && echo "libnvidia-opencl.so.1" > /etc/OpenCL/vendors/nvidia.icd
ENV TRANSFORMERS_CACHE=/root/.cache
COPY . .
# setting build related env vars
ENV CUDA_DOCKER_ARCH=all
ENV LLAMA_CUBLAS=1
# Install depencencies
RUN python -m pip install --upgrade pip pytest cmake \
scikit-build setuptools fastapi uvicorn sse-starlette \
pydantic-settings starlette-context gradio huggingface_hub hf_transfer
RUN CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
RUN CMAKE_ARGS="-DLLAMA_CUBLAS=on" FORCE_CMAKE=1 PIP_ROOT_USER_ACTION=ignore pip install --ignore-installed --timeout 100 -r requirements.txt
RUN useradd -m -u 1000 user
# Switch to the "user" user
USER user
# Set home to the user's home directory
ENV HOME=/home/user \
PATH=/home/user/.local/bin:$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
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 ["python", "app.py"]
|