CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-02 09:12:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

devops: add server build step

Browse Source 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
This commit is contained in:
Aaron Teo
2025-09-08 17:50:10 +08:00
parent e53e1c450c
commit e172b00445
1 changed files with 27 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

29
.devops/s390x.Dockerfile
View File

@@ -3,8 +3,9 @@ ARG UBUNTU_VERSION=24.10
FROM gcc:${GCC_VERSION} AS build
RUN apt-get update && \
apt-get install -y git cmake libcurl4-openssl-dev libopenblas-openmp-dev
RUN apt update && \
apt upgrade -y && \
apt install -y git cmake libcurl4-openssl-dev libopenblas-openmp-dev
WORKDIR /app
COPY . .
@@ -28,3 +29,27 @@ RUN cp *.py /opt/llama.cpp \
&& cp .devops/tools.sh /opt/llama.cpp/tools.sh
RUN ls -laR /opt/llama.cpp
FROM --platform=linux/s390x gcr.io/distroless/cc-debian12:nonroot AS server
ENV LLAMA_ARG_HOST=0.0.0.0
ENV LLAMA_ARG_PORT=8080
RUN apt update -y && \
apt upgrade -y && \
apt 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 /opt/llama.cpp/bin /
RUN ls -la | grep llama
WORKDIR /models
USER nonroot:nonroot
EXPOSE 8080
ENTRYPOINT [ "/llama-server" ]