ARG UBUNTU_VERSION=22.04

ARG MUSA_VERSION=rc4.3.0

ARG BASE_MUSA_DEV_CONTAINER=docker.io/mthreads/musa:${MUSA_VERSION}-devel-ubuntu${UBUNTU_VERSION}-amd64

ARG BASE_MUSA_RUN_CONTAINER=docker.io/mthreads/musa:${MUSA_VERSION}-runtime-ubuntu${UBUNTU_VERSION}-amd64

ARG BUILD_DATE=N/A

ARG APP_VERSION=N/A

ARG APP_REVISION=N/A

ARG NODE_VERSION=24

FROM docker.io/node:$NODE_VERSION AS web

ARG APP_VERSION

WORKDIR /app/tools/ui

COPY tools/ui/package.json tools/ui/package-lock.json ./

RUN npm ci

COPY tools/ui/ ./

RUN LLAMA_BUILD_NUMBER="$APP_VERSION" npm run build

FROM ${BASE_MUSA_DEV_CONTAINER} AS build

ARG MUSA_DOCKER_ARCH=default

RUN apt-get update && \

apt-get install -y \

build-essential \

cmake \

python3 \

python3-pip \

git \

libssl-dev \

libgomp1

WORKDIR /app

COPY . .

COPY --from=web /app/tools/ui/dist tools/ui/dist

RUN if [ "${MUSA_DOCKER_ARCH}" != "default" ]; then \

export CMAKE_ARGS="-DMUSA_ARCHITECTURES=${MUSA_DOCKER_ARCH}"; \

fi && \

cmake -B build -DGGML_NATIVE=OFF -DGGML_MUSA=ON -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON -DLLAMA_BUILD_TESTS=OFF ${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 -P {} /app/lib \;

RUN mkdir -p /app/full \

&& cp build/bin/* /app/full \

&& cp *.py /app/full \

&& cp -r conversion /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

FROM ${BASE_MUSA_RUN_CONTAINER} AS base

ARG BUILD_DATE=N/A

ARG APP_VERSION=N/A

ARG APP_REVISION=N/A

ARG IMAGE_URL=https://github.com/ggml-org/llama.cpp

ARG IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp

LABEL org.opencontainers.image.created=$BUILD_DATE \

org.opencontainers.image.version=$APP_VERSION \

org.opencontainers.image.revision=$APP_REVISION \

org.opencontainers.image.title="llama.cpp" \

org.opencontainers.image.description="LLM inference in C/C++" \

org.opencontainers.image.url=$IMAGE_URL \

org.opencontainers.image.source=$IMAGE_SOURCE

RUN apt-get update \

&& apt-get install -y libgomp1 curl ffmpeg \

&& 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

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"]

FROM base AS light

COPY --from=build /app/full/llama /app/full/llama-cli /app/full/llama-completion /app

WORKDIR /app

ENTRYPOINT [ "/app/llama-cli" ]

FROM base AS server

ENV LLAMA_ARG_HOST=0.0.0.0

COPY --from=build /app/full/llama /app/full/llama-server /app

WORKDIR /app

HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]

ENTRYPOINT [ "/app/llama-server" ]