mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-26 14:20:31 +01:00
39baaf55a1
* feat: add Dockerfiles for each platform that user ./server instead of ./main * feat: update .github/workflows/docker.yml to build server-first docker containers * doc: add information about running the server with Docker to README.md * doc: add information about running with docker to the server README * doc: update n-gpu-layers to show correct GPU usage * fix(doc): update container tag from `server` to `server-cuda` for README example on running server container with CUDA
26 lines
602 B
Docker
26 lines
602 B
Docker
ARG ONEAPI_VERSION=2024.0.1-devel-ubuntu22.04
|
|
ARG UBUNTU_VERSION=22.04
|
|
|
|
FROM intel/hpckit:$ONEAPI_VERSION as build
|
|
|
|
RUN apt-get update && \
|
|
apt-get install -y git
|
|
|
|
WORKDIR /app
|
|
|
|
COPY . .
|
|
|
|
# for some reasons, "-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=Intel10_64lp -DLLAMA_NATIVE=ON" give worse performance
|
|
RUN mkdir build && \
|
|
cd build && \
|
|
cmake .. -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx && \
|
|
cmake --build . --config Release --target main server
|
|
|
|
FROM ubuntu:$UBUNTU_VERSION as runtime
|
|
|
|
COPY --from=build /app/build/bin/server /server
|
|
|
|
ENV LC_ALL=C.utf8
|
|
|
|
ENTRYPOINT [ "/server" ]
|