llama.cpp/.devops/vulkan.Dockerfile

ARG UBUNTU_VERSION=24.04

FROM ubuntu:$UBUNTU_VERSION AS build

# Install build tools
RUN apt update && apt install -y git build-essential cmake wget

# Install Vulkan SDK and cURL
RUN wget -qO - https://packages.lunarg.com/lunarg-signing-key-pub.asc | apt-key add - && \
    wget -qO /etc/apt/sources.list.d/lunarg-vulkan-noble.list https://packages.lunarg.com/vulkan/lunarg-vulkan-noble.list && \
    apt update -y && \
    apt-get install -y vulkan-sdk libcurl4-openssl-dev curl

# Build it
WORKDIR /app

COPY . .

RUN cmake -B build -DGGML_NATIVE=OFF -DGGML_VULKAN=1 -DLLAMA_CURL=1 && \
    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 ubuntu:$UBUNTU_VERSION AS base

RUN apt-get update \
    && apt-get install -y libgomp1 curl libvulkan-dev \
    && 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-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" ]