devops: add s390x containers (#15915)

* devops: add s390x dockerfile Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: add missing ninja Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: move s390x docker into cpu docker Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: rework s390x docker Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: copy more tools Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: add server build step Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: remove apt clean steps as distroless misses it Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: remove apt commands from distroless Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: fix shared libs in distroless Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: use correct libs path Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: fix shared libs Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: add collector stage Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: fix missing stage ref Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: fix permission issue Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: fix unknown model loading failures Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: attempt at fixing model loading failure Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: fix missing ggml shared object failure to load model Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: remove move shared objects Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: move libggml-cpu and blas into bin Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: finalise hardened server stage Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: add cli target Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: fix typos Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: fix missing shared libraries in base Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: update debian target Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: formalise llama.cpp loc Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * Revert "devops: formalise llama.cpp loc" This reverts commit 0a7664af84. Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: formalise llama.cpp loc Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> (cherry picked from commit 0a7664af84) Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: attempt at fixing missing dir Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: attempt at making it cache the build Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: fix copying process Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: make build dir an argument Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * Revert "devops: make build dir an argument" This reverts commit 438698976b. Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: add build stage for gguf-py Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: move gguf-py installation into build stage Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: break system packages? Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: add rust compiler installer Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: fix rustc not found Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: remove cache mount to allow rustc to persist Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: move rustc installation to another layer Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: move gguf-py installation to full stage, fix copying Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: remove rustc installation in build Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: disable full target for now Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: attempting static build Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: merge s390x dockerfile into cpu for now Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: switch to gcc image for build step Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: remove build essentials Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: install openblas into base target Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: go back to s390x dockerfile Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: remove libggml and libblas Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: add full target Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: add break system packages Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: add libjpeg Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: add missing cmake dep Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: finalise docker images for s390x Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: add custom openblas patch Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: use libopenblas-dev instead of libopenblas-openmp-dev Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * devops: add s390x docker build Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> --------- Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-10-27 08:21:30 +00:00 · 2025-09-23 13:59:34 +08:00
parent 85e72271ba
commit 4b9f4cb0f8
2 changed files with 123 additions and 0 deletions
--- a/.devops/s390x.Dockerfile
+++ b/.devops/s390x.Dockerfile
@@ -0,0 +1,122 @@
+ARG GCC_VERSION=15.2.0
+ARG UBUNTU_VERSION=24.04
+
+### Build Llama.cpp stage
+FROM --platform=linux/s390x gcc:${GCC_VERSION} AS build
+
+RUN --mount=type=cache,target=/var/cache/apt \
+    --mount=type=cache,target=/var/lib/apt/lists \
+    apt update -y && \
+    apt upgrade -y && \
+    apt install -y --no-install-recommends \
+        git cmake ccache ninja-build \
+        # WARNING: Do not use libopenblas-openmp-dev. libopenblas-dev is faster.
+        libopenblas-dev libcurl4-openssl-dev && \
+    rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+COPY . .
+
+RUN --mount=type=cache,target=/root/.ccache \
+    --mount=type=cache,target=/app/build \
+    cmake -S . -B build -G Ninja \
+        -DCMAKE_BUILD_TYPE=Release \
+        -DCMAKE_C_COMPILER_LAUNCHER=ccache \
+        -DCMAKE_CXX_COMPILER_LAUNCHER=ccache \
+        -DLLAMA_BUILD_TESTS=OFF \
+        -DGGML_BACKEND_DL=OFF \
+        -DGGML_NATIVE=OFF \
+        -DGGML_BLAS=ON \
+        -DGGML_BLAS_VENDOR=OpenBLAS && \
+    cmake --build build --config Release -j $(nproc) && \
+    cmake --install build --prefix /opt/llama.cpp
+
+COPY *.py             /opt/llama.cpp/bin
+COPY .devops/tools.sh /opt/llama.cpp/bin
+
+COPY gguf-py          /opt/llama.cpp/gguf-py
+COPY requirements.txt /opt/llama.cpp/gguf-py
+COPY requirements     /opt/llama.cpp/gguf-py/requirements
+
+
+### Collect all llama.cpp binaries, libraries and distro libraries
+FROM --platform=linux/s390x scratch AS collector
+
+# Copy llama.cpp binaries and libraries
+COPY --from=build /opt/llama.cpp/bin     /llama.cpp/bin
+COPY --from=build /opt/llama.cpp/lib     /llama.cpp/lib
+COPY --from=build /opt/llama.cpp/gguf-py /llama.cpp/gguf-py
+
+
+### Base image
+FROM --platform=linux/s390x ubuntu:${UBUNTU_VERSION} AS base
+
+RUN --mount=type=cache,target=/var/cache/apt \
+    --mount=type=cache,target=/var/lib/apt/lists \
+    apt update -y && \
+    apt install -y --no-install-recommends \
+        # WARNING: Do not use libopenblas-openmp-dev. libopenblas-dev is faster.
+        curl libgomp1 libopenblas-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 llama.cpp libraries
+COPY --from=collector /llama.cpp/lib /usr/lib/s390x-linux-gnu
+
+
+### Full
+FROM --platform=linux/s390x base AS full
+
+ENV PATH="/root/.cargo/bin:${PATH}"
+WORKDIR /app
+
+RUN --mount=type=cache,target=/var/cache/apt \
+    --mount=type=cache,target=/var/lib/apt/lists \
+    apt update -y && \
+    apt install -y \
+        git cmake libjpeg-dev \
+        python3 python3-pip python3-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
+
+RUN curl https://sh.rustup.rs -sSf | bash -s -- -y
+
+COPY --from=collector /llama.cpp/bin /app
+COPY --from=collector /llama.cpp/gguf-py /app/gguf-py
+
+RUN pip install --no-cache-dir --break-system-packages \
+        -r /app/gguf-py/requirements.txt
+
+ENTRYPOINT [ "/app/tools.sh" ]
+
+
+### CLI Only
+FROM --platform=linux/s390x base AS light
+
+WORKDIR /llama.cpp/bin
+
+# Copy llama.cpp binaries and libraries
+COPY --from=collector /llama.cpp/bin/llama-cli /llama.cpp/bin
+
+ENTRYPOINT [ "/llama.cpp/bin/llama-cli" ]
+
+
+### Server
+FROM --platform=linux/s390x base AS server
+
+ENV LLAMA_ARG_HOST=0.0.0.0
+
+WORKDIR /llama.cpp/bin
+
+# Copy llama.cpp binaries and libraries
+COPY --from=collector /llama.cpp/bin/llama-server /llama.cpp/bin
+
+EXPOSE 8080
+
+ENTRYPOINT [ "/llama.cpp/bin/llama-server" ]
--- a/.github/workflows/docker.yml
+++ b/.github/workflows/docker.yml
@@ -44,6 +44,7 @@ jobs:
          - { tag: "musa", dockerfile: ".devops/musa.Dockerfile", platforms: "linux/amd64", full: true, light: true, server: true, free_disk_space: true }
          - { tag: "intel", dockerfile: ".devops/intel.Dockerfile", platforms: "linux/amd64", full: true, light: true, server: true, free_disk_space: true }
          - { tag: "vulkan", dockerfile: ".devops/vulkan.Dockerfile", platforms: "linux/amd64", full: true, light: true, server: true, free_disk_space: false }
+          - { tag: "s390x", dockerfile: ".devops/s390x.Dockerfile", platforms: "linux/s390x", full: true, light: true, server: true, free_disk_space: false }
          # Note: the rocm images are failing due to a compiler error and are disabled until this is fixed to allow the workflow to complete
          #- {tag: "rocm", dockerfile: ".devops/rocm.Dockerfile", platforms: "linux/amd64,linux/arm64", full: true, light: true, server: true, free_disk_space: true }
    steps: