mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-11-14 14:59:52 +00:00
cf8e0a3bb9
* mtgpu: add docker image support Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com> * mtgpu: enable docker workflow Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com> --------- Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
36 lines
1.2 KiB
Docker
36 lines
1.2 KiB
Docker
ARG UBUNTU_VERSION=22.04
|
|
# This needs to generally match the container host's environment.
|
|
ARG MUSA_VERSION=rc3.1.0
|
|
# Target the MUSA build image
|
|
ARG BASE_MUSA_DEV_CONTAINER=mthreads/musa:${MUSA_VERSION}-devel-ubuntu${UBUNTU_VERSION}
|
|
# Target the MUSA runtime image
|
|
ARG BASE_MUSA_RUN_CONTAINER=mthreads/musa:${MUSA_VERSION}-runtime-ubuntu${UBUNTU_VERSION}
|
|
|
|
FROM ${BASE_MUSA_DEV_CONTAINER} AS build
|
|
|
|
RUN apt-get update && \
|
|
apt-get install -y build-essential git cmake libcurl4-openssl-dev
|
|
|
|
WORKDIR /app
|
|
|
|
COPY . .
|
|
|
|
RUN cmake -B build -DGGML_MUSA=ON -DLLAMA_CURL=ON ${CMAKE_ARGS} -DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined . && \
|
|
cmake --build build --config Release --target llama-server -j$(nproc)
|
|
|
|
FROM ${BASE_MUSA_RUN_CONTAINER} AS runtime
|
|
|
|
RUN apt-get update && \
|
|
apt-get install -y libcurl4-openssl-dev libgomp1 curl
|
|
|
|
COPY --from=build /app/build/ggml/src/libggml.so /libggml.so
|
|
COPY --from=build /app/build/src/libllama.so /libllama.so
|
|
COPY --from=build /app/build/bin/llama-server /llama-server
|
|
|
|
# Must be set to 0.0.0.0 so it can listen to requests from host machine
|
|
ENV LLAMA_ARG_HOST=0.0.0.0
|
|
|
|
HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
|
|
|
|
ENTRYPOINT [ "/llama-server" ]
|