llama.cpp/.devops/intel.Dockerfile at master · CrazyForks/llama.cpp · GitHub

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
135
ARG ONEAPI_VERSION=2025.3.3-0-devel-ubuntu24.04
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A

## Build Image

FROM intel/deep-learning-essentials:$ONEAPI_VERSION AS build

ARG GGML_SYCL_F16=OFF
ARG LEVEL_ZERO_VERSION=1.28.2
ARG LEVEL_ZERO_UBUNTU_VERSION=u24.04
RUN apt-get update && \
    apt-get install -y git libssl-dev wget ca-certificates && \
    cd /tmp && \
    wget -q "https://github.com/oneapi-src/level-zero/releases/download/v${LEVEL_ZERO_VERSION}/level-zero_${LEVEL_ZERO_VERSION}%2B${LEVEL_ZERO_UBUNTU_VERSION}_amd64.deb" -O level-zero.deb && \
    wget -q "https://github.com/oneapi-src/level-zero/releases/download/v${LEVEL_ZERO_VERSION}/level-zero-devel_${LEVEL_ZERO_VERSION}%2B${LEVEL_ZERO_UBUNTU_VERSION}_amd64.deb" -O level-zero-devel.deb && \
    apt-get -o Dpkg::Options::="--force-overwrite" install -y ./level-zero.deb ./level-zero-devel.deb && \
    rm -f /tmp/level-zero.deb /tmp/level-zero-devel.deb

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 -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON -DLLAMA_BUILD_TESTS=OFF ${OPT_SYCL_F16} && \
    cmake --build build --config Release -j$(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 intel/deep-learning-essentials:$ONEAPI_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

ARG IGC_VERSION=v2.20.5
ARG IGC_VERSION_FULL=2_2.20.5+19972
ARG COMPUTE_RUNTIME_VERSION=25.40.35563.10
ARG COMPUTE_RUNTIME_VERSION_FULL=25.40.35563.10-0
ARG IGDGMM_VERSION=22.8.2
RUN mkdir /tmp/neo/ && cd /tmp/neo/ \
  && wget https://github.com/intel/intel-graphics-compiler/releases/download/$IGC_VERSION/intel-igc-core-${IGC_VERSION_FULL}_amd64.deb \
  && wget https://github.com/intel/intel-graphics-compiler/releases/download/$IGC_VERSION/intel-igc-opencl-${IGC_VERSION_FULL}_amd64.deb \
  && wget https://github.com/intel/compute-runtime/releases/download/$COMPUTE_RUNTIME_VERSION/intel-ocloc-dbgsym_${COMPUTE_RUNTIME_VERSION_FULL}_amd64.ddeb \
  && wget https://github.com/intel/compute-runtime/releases/download/$COMPUTE_RUNTIME_VERSION/intel-ocloc_${COMPUTE_RUNTIME_VERSION_FULL}_amd64.deb \
  && wget https://github.com/intel/compute-runtime/releases/download/$COMPUTE_RUNTIME_VERSION/intel-opencl-icd-dbgsym_${COMPUTE_RUNTIME_VERSION_FULL}_amd64.ddeb \
  && wget https://github.com/intel/compute-runtime/releases/download/$COMPUTE_RUNTIME_VERSION/intel-opencl-icd_${COMPUTE_RUNTIME_VERSION_FULL}_amd64.deb \
  && wget https://github.com/intel/compute-runtime/releases/download/$COMPUTE_RUNTIME_VERSION/libigdgmm12_${IGDGMM_VERSION}_amd64.deb \
  && wget https://github.com/intel/compute-runtime/releases/download/$COMPUTE_RUNTIME_VERSION/libze-intel-gpu1-dbgsym_${COMPUTE_RUNTIME_VERSION_FULL}_amd64.ddeb \
  && wget https://github.com/intel/compute-runtime/releases/download/$COMPUTE_RUNTIME_VERSION/libze-intel-gpu1_${COMPUTE_RUNTIME_VERSION_FULL}_amd64.deb \
  && dpkg --install *.deb

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 \
        python3-venv && \
    python3 -m venv /opt/venv && \
    . /opt/venv/bin/activate && \
    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

ENV PATH="/opt/venv/bin:$PATH"

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

WORKDIR /app

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

ENTRYPOINT [ "/app/llama-server" ]