File size: 3,789 Bytes
22510af
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
ARG UBUNTU_VERSION=24.04
# This needs to generally match the container host's environment.
ARG CUDA_VERSION=12.8.1
ARG GCC_VERSION=14
# Target the CUDA build image
ARG BASE_CUDA_DEV_CONTAINER=docker.io/nvidia/cuda:${CUDA_VERSION}-devel-ubuntu${UBUNTU_VERSION}

ARG BASE_CUDA_RUN_CONTAINER=docker.io/nvidia/cuda:${CUDA_VERSION}-runtime-ubuntu${UBUNTU_VERSION}

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_CUDA_DEV_CONTAINER} AS build

ARG GCC_VERSION
# CUDA architecture to build for (defaults to all supported archs)
ARG CUDA_DOCKER_ARCH=default

RUN apt-get update && \
    apt-get install -y gcc-${GCC_VERSION} g++-${GCC_VERSION} build-essential cmake python3 python3-pip git libssl-dev libgomp1

ENV CC=gcc-${GCC_VERSION} CXX=g++-${GCC_VERSION} CUDAHOSTCXX=g++-${GCC_VERSION}

WORKDIR /app

COPY . .

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

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 -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

## Base image
FROM ${BASE_CUDA_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

### 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" ]