koboldcpp/.devops/llama-cli-cann.Dockerfile
SamareshSingh 5cbaa5e69e
docker : add OCI image labels for version and build date (#21653)
* 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>
2026-05-18 22:14:45 +02:00

62 lines
2.9 KiB
Docker

ARG ASCEND_VERSION=8.5.0-910b-openeuler22.03-py3.10
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
FROM ascendai/cann:$ASCEND_VERSION AS build
WORKDIR /app
COPY . .
RUN yum install -y gcc g++ cmake make openssl-devel
ENV ASCEND_TOOLKIT_HOME=/usr/local/Ascend/ascend-toolkit/latest
ENV LIBRARY_PATH=${ASCEND_TOOLKIT_HOME}/lib64:$LIBRARY_PATH
ENV LD_LIBRARY_PATH=${ASCEND_TOOLKIT_HOME}/lib64:${ASCEND_TOOLKIT_HOME}/lib64/plugin/opskernel:${ASCEND_TOOLKIT_HOME}/lib64/plugin/nnengine:${ASCEND_TOOLKIT_HOME}/opp/built-in/op_impl/ai_core/tbe/op_tiling:${LD_LIBRARY_PATH}
ENV PYTHONPATH=${ASCEND_TOOLKIT_HOME}/python/site-packages:${ASCEND_TOOLKIT_HOME}/opp/built-in/op_impl/ai_core/tbe:${PYTHONPATH}
ENV PATH=${ASCEND_TOOLKIT_HOME}/bin:${ASCEND_TOOLKIT_HOME}/compiler/ccec_compiler/bin:${PATH}
ENV ASCEND_AICPU_PATH=${ASCEND_TOOLKIT_HOME}
ENV ASCEND_OPP_PATH=${ASCEND_TOOLKIT_HOME}/opp
ENV TOOLCHAIN_HOME=${ASCEND_TOOLKIT_HOME}/toolkit
ENV ASCEND_HOME_PATH=${ASCEND_TOOLKIT_HOME}
# find libascend_hal.so, because the drive hasn`t been mounted.
ENV LD_LIBRARY_PATH=${ASCEND_TOOLKIT_HOME}/runtime/lib64/stub:$LD_LIBRARY_PATH
RUN echo "Building with static libs" && \
source /usr/local/Ascend/ascend-toolkit/set_env.sh --force && \
cmake -B build -DGGML_NATIVE=OFF -DGGML_CANN=ON -DBUILD_SHARED_LIBS=OFF -DLLAMA_BUILD_TESTS=OFF && \
cmake --build build --config Release --target llama-cli && \
cmake --build build --config Release --target llama-completion
# TODO: use image with NNRT
FROM ascendai/cann:$ASCEND_VERSION AS runtime
ARG BUILD_DATE=N/A
ARG APP_VERSION=N/A
ARG APP_REVISION=N/A
ARG IMAGE_URL=https://github.com/ggml-org/llama.cpp
ARG IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp
LABEL org.opencontainers.image.created=$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
COPY --from=build /app/build/bin/llama-cli /app/build/bin/llama-completion /
ENV LC_ALL=C.utf8
ENV ASCEND_TOOLKIT_HOME=/usr/local/Ascend/ascend-toolkit/latest
ENV LIBRARY_PATH=${ASCEND_TOOLKIT_HOME}/lib64:$LIBRARY_PATH
ENV LD_LIBRARY_PATH=${ASCEND_TOOLKIT_HOME}/lib64:${ASCEND_TOOLKIT_HOME}/lib64/plugin/opskernel:${ASCEND_TOOLKIT_HOME}/lib64/plugin/nnengine:${ASCEND_TOOLKIT_HOME}/opp/built-in/op_impl/ai_core/tbe/op_tiling:${LD_LIBRARY_PATH}
ENV PYTHONPATH=${ASCEND_TOOLKIT_HOME}/python/site-packages:${ASCEND_TOOLKIT_HOME}/opp/built-in/op_impl/ai_core/tbe:${PYTHONPATH}
ENV PATH=${ASCEND_TOOLKIT_HOME}/bin:${ASCEND_TOOLKIT_HOME}/compiler/ccec_compiler/bin:${PATH}
ENV ASCEND_AICPU_PATH=${ASCEND_TOOLKIT_HOME}
ENV ASCEND_OPP_PATH=${ASCEND_TOOLKIT_HOME}/opp
ENV TOOLCHAIN_HOME=${ASCEND_TOOLKIT_HOME}/toolkit
ENV ASCEND_HOME_PATH=${ASCEND_TOOLKIT_HOME}
ENTRYPOINT ["/llama-cli" ]