backend/llama.cpp/.devops/cpu.Dockerfile

ARG UBUNTU_VERSION=24.04
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 docker.io/ubuntu:$UBUNTU_VERSION AS build

ARG TARGETARCH

RUN apt-get update && \
    apt-get install -y gcc-14 g++-14 build-essential git cmake libssl-dev

ENV CC=gcc-14 CXX=g++-14

WORKDIR /app

COPY . .

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

RUN if [ "$TARGETARCH" = "amd64" ] || [ "$TARGETARCH" = "arm64" ]; then \
        cmake -S . -B build -DCMAKE_BUILD_TYPE=Release -DGGML_NATIVE=OFF -DLLAMA_BUILD_TESTS=OFF -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON; \
    else \
        echo "Unsupported architecture"; \
        exit 1; \
    fi && \
    cmake --build build -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

## Base image
FROM docker.io/ubuntu:$UBUNTU_VERSION 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

### 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 \
    python3-wheel \
    && pip install --break-system-packages --upgrade setuptools \
    && pip install --break-system-packages -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 /app/full/llama-cli /app/full/llama-completion /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 /app/full/llama-server /app

WORKDIR /app

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

ENTRYPOINT [ "/app/llama-server" ]