Spaces:
Paused
Paused
File size: 1,244 Bytes
22d91a3 8b4dc3e 175eaf8 82c5f09 175eaf8 22d91a3 175eaf8 22d91a3 41adfc5 e60e653 c86bf80 e60e653 175eaf8 |
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 |
# 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:11.7.1-runtime-ubuntu22.04
RUN apt-get update && apt-get upgrade -y \
&& apt-get install -y git build-essential libpq-dev \
python3 python3-pip gcc wget \
ocl-icd-opencl-dev opencl-headers clinfo \
libclblast-dev libopenblas-dev \
&& mkdir -p /etc/OpenCL/vendors && echo "libnvidia-opencl.so.1" > /etc/OpenCL/vendors/nvidia.icd
RUN apt-get update && apt-get install -y software-properties-common
RUN apt-get install -y g++-11
ENV TRANSFORMERS_CACHE=/root/.cache
COPY . .
# setting build related env vars
ENV CUDA_DOCKER_ARCH=all
ENV LLAMA_CUBLAS=1
# Install depencencies
RUN python3 -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" FORCE_CMAKE=1 pip install llama-cpp-python
RUN CMAKE_ARGS="-DLLAMA_CUBLAS=on" FORCE_CMAKE=1 pip install --timeout 100 -r requirements.txt
RUN chmod +x ./run.sh
CMD ./run.sh
|