baalajimaestro/llama.cpp
1
0
Fork 0
Code Issues Pull requests Packages Projects Releases Wiki Activity

Merge pull request #598 from pradhyumna85/main

Browse source 
Fixed Cuda Dockerfile
This commit is contained in:
Andrei 2023-08-17 23:20:43 -04:00 committed by GitHub
parent 8fc3fa9f1c d010ea70d2
commit 4cf0461f97
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 14 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

17
docker/cuda_simple/Dockerfile
View file

@ -4,13 +4,24 @@ 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
RUN apt-get update && apt-get upgrade -y \
&& apt-get install -y git build-essential \
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
COPY . .
# Install the package
RUN apt update && apt install -y python3 python3-pip
# 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
RUN LLAMA_CUBLAS=1 pip install llama-cpp-python
# Install llama-cpp-python (build with cuda)
RUN CMAKE_ARGS="-DLLAMA_CUBLAS=on" FORCE_CMAKE=1 pip install llama-cpp-python
# Run the server
CMD python3 -m llama_cpp.server