llama.cpp/docker/cuda_simple/Dockerfile

16 lines
445 B
Docker

ARG CUDA_IMAGE="12.1.1-devel-ubuntu22.04"
FROM nvidia/cuda:${CUDA_IMAGE}
# We need to set the host to 0.0.0.0 to allow outside access
ENV HOST 0.0.0.0
COPY . .
# Install the package
RUN apt update && apt install -y python3 python3-pip
RUN python3 -m pip install --upgrade pip pytest cmake scikit-build setuptools fastapi uvicorn sse-starlette
RUN LLAMA_CUBLAS=1 pip install llama-cpp-python
# Run the server
CMD python3 -m llama_cpp.server