mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2026-05-23 21:13:36 +00:00
5cbaa5e69e
* docker: add OCI image labels to all published images * docker: propagate OCI labels as manifest and index annotations * docker: drop hardcoded org URL and revert accidental intel version bump The OCI image url and source are now driven by build args with a sensible default. The workflow passes the actual repository url so fork builds get labels pointing at the fork instead of upstream. Also restores the IGC, compute runtime, and IGDGMM versions in the intel Dockerfile labeled stage which I accidentally bumped in the first commit. * docker: add skip_s390x workflow_dispatch input for fast test runs Lets maintainers and PR authors trigger the docker workflow without the s390x build target, which depends on the IBM Z runner and is by far the slowest job in the matrix. The flag filters the s390x row out of the build matrix before merge_matrix is derived, so the merge job sees a consistent shape too. Signed-off-by: Samaresh Kumar Singh <ssam3003@gmail.com> --------- Signed-off-by: Samaresh Kumar Singh <ssam3003@gmail.com>
134 lines
5.2 KiB
Docker
134 lines
5.2 KiB
Docker
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 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" ]
|