llama.cpp/.devops/intel.Dockerfile

ARG ONEAPI_VERSION=2025.0.0-0-devel-ubuntu22.04

## Build Image

FROM intel/oneapi-basekit:$ONEAPI_VERSION AS build

ARG GGML_SYCL_F16=OFF
RUN apt-get update && \
    apt-get install -y git libcurl4-openssl-dev

WORKDIR /app

COPY . .

RUN if [ "${GGML_SYCL_F16}" = "ON" ]; then \
        echo "GGML_SYCL_F16 is set" \
        && export OPT_SYCL_F16="-DGGML_SYCL_F16=ON"; \
    fi && \
    echo "Building with dynamic libs" && \
    cmake -B build -DGGML_NATIVE=OFF -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DLLAMA_CURL=ON ${OPT_SYCL_F16} && \
    cmake --build build --config Release -j$(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

FROM intel/oneapi-basekit:$ONEAPI_VERSION 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

### Full
FROM base AS full

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

WORKDIR /app

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

ENTRYPOINT [ "/app/llama-server" ]