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: finalise hardened server stage

Browse Source 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
This commit is contained in:
Aaron Teo
2025-09-09 16:59:53 +08:00
parent 10714efb6d
commit f6baab6be8
1 changed files with 3 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
.devops/s390x.Dockerfile
View File

@@ -40,12 +40,14 @@ COPY --from=build /opt/llama.cpp/lib /lib/llama.cpp
# Copy all shared libraries from distro # Copy all shared libraries from distro
COPY --from=build /usr/lib/s390x-linux-gnu /lib/distro COPY --from=build /usr/lib/s390x-linux-gnu /lib/distro
### Hardened Server
FROM --platform=linux/s390x gcr.io/distroless/cc-debian12:nonroot AS server FROM --platform=linux/s390x gcr.io/distroless/cc-debian12:nonroot AS server
ENV LLAMA_ARG_HOST=0.0.0.0 ENV LLAMA_ARG_HOST=0.0.0.0
# Copy llama.cpp binaries and libraries # Copy llama.cpp binaries and libraries
COPY --from=collector /bin/llama.cpp / COPY --from=collector /bin/llama.cpp/llama-server /
COPY --from=collector /lib/llama.cpp /usr/lib/s390x-linux-gnu COPY --from=collector /lib/llama.cpp /usr/lib/s390x-linux-gnu
# Fixes model loading errors # Fixes model loading errors