CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-04 09:32:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

devops: rework s390x docker

Browse Source 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
This commit is contained in:
Aaron Teo
2025-09-08 15:19:41 +08:00
parent 955c426620
commit ce7bd1955d
2 changed files with 18 additions and 82 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
.devops/cpu.Dockerfile
View File

@@ -1,6 +1,7 @@
ARG UBUNTU_VERSION=22.04 ARG GCC_VERSION=15.2.0
ARG UBUNTU_VERSION=24.10
FROM ubuntu:$UBUNTU_VERSION AS build FROM gcc:${GCC_VERSION} AS build
ARG TARGETARCH ARG TARGETARCH
@@ -13,6 +14,8 @@ COPY . .
RUN if [ "$TARGETARCH" = "amd64" ] || [ "$TARGETARCH" = "arm64" ]; then \ RUN if [ "$TARGETARCH" = "amd64" ] || [ "$TARGETARCH" = "arm64" ]; then \
cmake -S . -B build -DCMAKE_BUILD_TYPE=Release -DGGML_NATIVE=OFF -DLLAMA_BUILD_TESTS=OFF -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON; \ cmake -S . -B build -DCMAKE_BUILD_TYPE=Release -DGGML_NATIVE=OFF -DLLAMA_BUILD_TESTS=OFF -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON; \
elif [ "${TARGETARCH}" = "s390x" ]; then \
cmake -S . -B build -DCMAKE_BUILD_TYPE=Release -DGGML_NATIVE=OFF -DLLAMA_BUILD_TESTS=OFF -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=OFF; \
else \ else \
echo "Unsupported architecture"; \ echo "Unsupported architecture"; \
exit 1; \ exit 1; \

93
.devops/s390x.Dockerfile
View File

@@ -3,89 +3,22 @@ ARG UBUNTU_VERSION=24.10
FROM gcc:${GCC_VERSION} AS build FROM gcc:${GCC_VERSION} AS build
ARG TARGETARCH
RUN apt-get update && \ RUN apt-get update && \
apt-get install -y build-essential git cmake libcurl4-openssl-dev apt-get install -y git cmake libcurl4-openssl-dev libopenblas-openmp-dev
WORKDIR /app WORKDIR /app
COPY . . COPY . .
RUN if [ "$TARGETARCH" = "amd64" ] || [ "$TARGETARCH" = "arm64" ]; then \ RUN --mount=type=cache,target=/root/.ccache \
cmake -S . -B build -DCMAKE_BUILD_TYPE=Release -DGGML_NATIVE=OFF -DLLAMA_BUILD_TESTS=OFF -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON; \ cmake -S . -B build \
elif [ "${TARGETARCH}" = "s390x" ]; then \ -DCMAKE_BUILD_TYPE=Release \
cmake -S . -B build -DCMAKE_BUILD_TYPE=Release -DGGML_NATIVE=OFF -DLLAMA_BUILD_TESTS=OFF -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=OFF; \ -DLLAMA_BUILD_TESTS=OFF \
else \ -DGGML_NATIVE=OFF \
echo "Unsupported architecture"; \ -DGGML_BACKEND_DL=ON \
exit 1; \ -DGGML_CPU_ALL_VARIANTS=OFF \
fi && \ -DGGML_BLAS=ON \
cmake --build build -j $(nproc) -DGGML_BLAS_VENDOR=OpenBLAS \
&& cmake --build build --config Release -j $(nproc) \
&& cmake --install build --prefix /opt/llama.cpp
RUN mkdir -p /app/lib && \ RUN ls -la /opt/llama.cpp
find build -name "*.so" -exec cp {} /app/lib \;
RUN mkdir -p /app/full \
&& cp build/bin/* /app/full \
&& cp *.py /app/full \
&& cp -r gguf-py /app/full \
&& cp -r requirements /app/full \
&& cp requirements.txt /app/full \
&& cp .devops/tools.sh /app/full/tools.sh
## Base image
FROM ubuntu:$UBUNTU_VERSION AS base
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
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 \
&& 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
ENTRYPOINT ["/app/tools.sh"]
### Light, CLI only
FROM base AS light
COPY --from=build /app/full/llama-cli /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-server /app
WORKDIR /app
HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
ENTRYPOINT [ "/app/llama-server" ]