Upstream ghcr.io/ggml-org/llama.cpp:server-cuda has moved past the digest pinned in server/Dockerfile.cuda.
|
digest |
| pinned |
sha256:7b3d7834fc7307cb54f24f8869b67bfff276404c416452a48d11321bc36a81be |
| current |
sha256:fd68d13013141833e8214ecad6e1fbefb532db6a00b980cdecfe33603dbf2675 |
To update
- Bump the
FROM ghcr.io/ggml-org/llama.cpp:server-cuda@sha256:… digest in server/Dockerfile.cuda to sha256:fd68d13013141833e8214ecad6e1fbefb532db6a00b980cdecfe33603dbf2675.
cd server && make scout-cuda to rebuild + scan (the shared-lib layout may have changed — the Dockerfile copies all /app/*.so* to stay robust).- Confirm
/app/llama-server still resolves all libs, then promote.
Auto-filed by the weekly llama.cpp pin freshness workflow.
Upstream
ghcr.io/ggml-org/llama.cpp:server-cudahas moved past the digest pinned inserver/Dockerfile.cuda.sha256:7b3d7834fc7307cb54f24f8869b67bfff276404c416452a48d11321bc36a81besha256:fd68d13013141833e8214ecad6e1fbefb532db6a00b980cdecfe33603dbf2675To update
FROM ghcr.io/ggml-org/llama.cpp:server-cuda@sha256:…digest inserver/Dockerfile.cudatosha256:fd68d13013141833e8214ecad6e1fbefb532db6a00b980cdecfe33603dbf2675.cd server && make scout-cudato rebuild + scan (the shared-lib layout may have changed — the Dockerfile copies all/app/*.so*to stay robust)./app/llama-serverstill resolves all libs, then promote.Auto-filed by the weekly
llama.cpp pin freshnessworkflow.