CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-06 09:46:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

devops: fix failing s390x docker build (#16918)

Browse Source
This commit is contained in:
Aaron Teo
2025-11-02 08:48:46 +08:00
committed by GitHub
parent d38d9f0877
commit a864132ba5
2 changed files with 7 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
.devops/s390x.Dockerfile
View File

@@ -24,8 +24,9 @@ RUN --mount=type=cache,target=/root/.ccache \
-DCMAKE_C_COMPILER_LAUNCHER=ccache \ -DCMAKE_C_COMPILER_LAUNCHER=ccache \
-DCMAKE_CXX_COMPILER_LAUNCHER=ccache \ -DCMAKE_CXX_COMPILER_LAUNCHER=ccache \
-DLLAMA_BUILD_TESTS=OFF \ -DLLAMA_BUILD_TESTS=OFF \
-DGGML_BACKEND_DL=OFF \
-DGGML_NATIVE=OFF \ -DGGML_NATIVE=OFF \
-DGGML_BACKEND_DL=ON \
-DGGML_CPU_ALL_VARIANTS=ON \
-DGGML_BLAS=ON \ -DGGML_BLAS=ON \
-DGGML_BLAS_VENDOR=OpenBLAS && \ -DGGML_BLAS_VENDOR=OpenBLAS && \
cmake --build build --config Release -j $(nproc) && \ cmake --build build --config Release -j $(nproc) && \
@@ -103,6 +104,7 @@ FROM base AS light
WORKDIR /llama.cpp/bin WORKDIR /llama.cpp/bin
# Copy llama.cpp binaries and libraries # Copy llama.cpp binaries and libraries
COPY --from=collector /llama.cpp/bin/*.so /llama.cpp/bin
COPY --from=collector /llama.cpp/bin/llama-cli /llama.cpp/bin COPY --from=collector /llama.cpp/bin/llama-cli /llama.cpp/bin
ENTRYPOINT [ "/llama.cpp/bin/llama-cli" ] ENTRYPOINT [ "/llama.cpp/bin/llama-cli" ]
@@ -116,6 +118,7 @@ ENV LLAMA_ARG_HOST=0.0.0.0
WORKDIR /llama.cpp/bin WORKDIR /llama.cpp/bin
# Copy llama.cpp binaries and libraries # Copy llama.cpp binaries and libraries
COPY --from=collector /llama.cpp/bin/*.so /llama.cpp/bin
COPY --from=collector /llama.cpp/bin/llama-server /llama.cpp/bin COPY --from=collector /llama.cpp/bin/llama-server /llama.cpp/bin
EXPOSE 8080 EXPOSE 8080

6
docs/docker.md
View File

@@ -7,9 +7,9 @@
## Images ## Images
We have three Docker images available for this project: We have three Docker images available for this project:
1. `ghcr.io/ggml-org/llama.cpp:full`: This image includes both the main executable file and the tools to convert LLaMA models into ggml and convert into 4-bit quantization. (platforms: `linux/amd64`, `linux/arm64`) 1. `ghcr.io/ggml-org/llama.cpp:full`: This image includes both the main executable file and the tools to convert LLaMA models into ggml and convert into 4-bit quantization. (platforms: `linux/amd64`, `linux/arm64`, `linux/s390x`)
2. `ghcr.io/ggml-org/llama.cpp:light`: This image only includes the main executable file. (platforms: `linux/amd64`, `linux/arm64`) 2. `ghcr.io/ggml-org/llama.cpp:light`: This image only includes the main executable file. (platforms: `linux/amd64`, `linux/arm64`, `linux/s390x`)
3. `ghcr.io/ggml-org/llama.cpp:server`: This image only includes the server executable file. (platforms: `linux/amd64`, `linux/arm64`) 3. `ghcr.io/ggml-org/llama.cpp:server`: This image only includes the server executable file. (platforms: `linux/amd64`, `linux/arm64`, `linux/s390x`)
Additionally, there the following images, similar to the above: Additionally, there the following images, similar to the above: