mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-26 03:14:35 +00:00
95 lines
2.4 KiB
Docker
95 lines
2.4 KiB
Docker
|
ARG UBUNTU_VERSION=22.04
|
||
|
|
# This needs to generally match the container host's environment.
|
||
|
|
ARG CUDA_VERSION=12.6.0
|
||
|
|
# Target the CUDA build image
|
||
|
|
ARG BASE_CUDA_DEV_CONTAINER=nvidia/cuda:${CUDA_VERSION}-devel-ubuntu${UBUNTU_VERSION}
|
||
|
|
|
||
|
|
ARG BASE_CUDA_RUN_CONTAINER=nvidia/cuda:${CUDA_VERSION}-runtime-ubuntu${UBUNTU_VERSION}
|
||
|
|
|
||
|
|
FROM ${BASE_CUDA_DEV_CONTAINER} AS build
|
||
|
|
|
||
|
|
# CUDA architecture to build for (defaults to all supported archs)
|
||
|
|
ARG CUDA_DOCKER_ARCH=default
|
||
|
|
|
||
|
|
RUN apt-get update && \
|
||
|
|
apt-get install -y build-essential cmake python3 python3-pip git libcurl4-openssl-dev libgomp1
|
||
|
|
|
||
|
|
WORKDIR /app
|
||
|
|
|
||
|
|
COPY . .
|
||
|
|
|
||
|
|
RUN if [ "${CUDA_DOCKER_ARCH}" != "default" ]; then \
|
||
|
|
export CMAKE_ARGS="-DCMAKE_CUDA_ARCHITECTURES=${CUDA_DOCKER_ARCH}"; \
|
||
|
|
fi && \
|
||
|
|
cmake -B build -DGGML_NATIVE=OFF -DGGML_CUDA=ON -DLLAMA_CURL=ON ${CMAKE_ARGS} -DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined . && \
|
||
|
|
cmake --build build --config Release -j$(nproc)
|
||
|
|
|
||
|
|
RUN mkdir -p /app/lib && \
|
||
|
|
find build -name "*.so" -exec cp {} /app/lib \;
|
||
|
|
|
||
|
|
RUN mkdir -p /app/full \
|
||
|
|
&& cp build/bin/* /app/full \
|
||
|
|
&& cp *.py /app/full \
|
||
|
|
&& cp -r gguf-py /app/full \
|
||
|
|
&& cp -r requirements /app/full \
|
||
|
|
&& cp requirements.txt /app/full \
|
||
|
|
&& cp .devops/tools.sh /app/full/tools.sh
|
||
|
|
|
||
|
|
## Base image
|
||
|
|
FROM ${BASE_CUDA_RUN_CONTAINER} AS base
|
||
|
|
|
||
|
|
RUN apt-get update \
|
||
|
|
&& apt-get install -y libgomp1 curl\
|
||
|
|
&& apt autoremove -y \
|
||
|
|
&& apt clean -y \
|
||
|
|
&& rm -rf /tmp/* /var/tmp/* \
|
||
|
|
&& find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete \
|
||
|
|
&& find /var/cache -type f -delete
|
||
|
|
|
||
|
|
COPY --from=build /app/lib/ /app
|
||
|
|
|
||
|
|
### Full
|
||
|
|
FROM base AS full
|
||
|
|
|
||
|
|
COPY --from=build /app/full /app
|
||
|
|
|
||
|
|
WORKDIR /app
|
||
|
|
|
||
|
|
RUN apt-get update \
|
||
|
|
&& apt-get install -y \
|
||
|
|
git \
|
||
|
|
python3 \
|
||
|
|
python3-pip \
|
||
|
|
&& pip install --upgrade pip setuptools wheel \
|
||
|
|
&& pip install -r requirements.txt \
|
||
|
|
&& apt autoremove -y \
|
||
|
|
&& apt clean -y \
|
||
|
|
&& rm -rf /tmp/* /var/tmp/* \
|
||
|
|
&& find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete \
|
||
|
|
&& find /var/cache -type f -delete
|
||
|
|
|
||
|
|
|
||
|
|
ENTRYPOINT ["/app/tools.sh"]
|
||
|
|
|
||
|
|
### Light, CLI only
|
||
|
|
FROM base AS light
|
||
|
|
|
||
|
|
COPY --from=build /app/full/llama-cli /app
|
||
|
|
|
||
|
|
WORKDIR /app
|
||
|
|
|
||
|
|
ENTRYPOINT [ "/app/llama-cli" ]
|
||
|
|
|
||
|
|
### Server, Server only
|
||
|
|
FROM base AS server
|
||
|
|
|
||
|
|
ENV LLAMA_ARG_HOST=0.0.0.0
|
||
|
|
|
||
|
|
COPY --from=build /app/full/llama-server /app
|
||
|
|
|
||
|
|
WORKDIR /app
|
||
|
|
|
||
|
|
HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
|
||
|
|
|
||
|
|
ENTRYPOINT [ "/app/llama-server" ]
|