Upstream ghcr.io/ggml-org/llama.cpp:server-cuda has moved past the digest pinned in server/Dockerfile.cuda.
|
digest |
| pinned |
sha256:d0cd0c4563e046f6ad0c8c27fe78280376d0d645cc3fef7a1ab87c75de08377b |
| current |
sha256:4c8e5e3dc25d6b044e90f7eecb2243920a15d2f09a7df67787b03229620c934e |
To update
- Bump the
FROM ghcr.io/ggml-org/llama.cpp:server-cuda@sha256:… digest in server/Dockerfile.cuda to sha256:4c8e5e3dc25d6b044e90f7eecb2243920a15d2f09a7df67787b03229620c934e.
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:d0cd0c4563e046f6ad0c8c27fe78280376d0d645cc3fef7a1ab87c75de08377bsha256:4c8e5e3dc25d6b044e90f7eecb2243920a15d2f09a7df67787b03229620c934eTo update
FROM ghcr.io/ggml-org/llama.cpp:server-cuda@sha256:…digest inserver/Dockerfile.cudatosha256:4c8e5e3dc25d6b044e90f7eecb2243920a15d2f09a7df67787b03229620c934e.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.