chore(server/cuda): bump pinned llama.cpp digest to 7b3d7834 - #141
Merged
Conversation
Upstream ghcr.io/ggml-org/llama.cpp:server-cuda moved past the pinned digest. New pin is llama.cpp build 9982 (99f3dc322). Verified on the prod RTX 3090 box before commit: - image builds; /app/llama-server resolves all shared libs (--version OK) - trivy HIGH/CRITICAL diff vs v0.12.1-cu128: no new findings; the cix-server binary is now clean (fresh Go toolchain dropped CVE-2026-39822); the cloudflared/ngrok findings are pre-existing and identical in both images - deployed to the cix stack and exercised end-to-end (health + GPU offload + embedding smoke), then restored Closes #140. Closes #136 (superseded by the same bump). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This was referenced Jul 13, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Bumps the pinned
ghcr.io/ggml-org/llama.cpp:server-cudadigest inserver/Dockerfile.cuda:sha256:d0cd0c4563e046f6ad0c8c27fe78280376d0d645cc3fef7a1ab87c75de08377bsha256:7b3d7834fc7307cb54f24f8869b67bfff276404c416452a48d11321bc36a81be(llama.cpp b9982,99f3dc322)Closes #140. Closes #136 (older digest, superseded by this one).
Verification (done before this PR, on the prod RTX 3090 box)
/app/llama-server --versionruns → all.sos resolve;--list-devicesreportsCUDA0: NVIDIA GeForce RTX 3090.v0.12.1-cu128): no new findings. Thecix-serverbinary is now clean — the fresh Go toolchain droppedCVE-2026-39822; thecloudflared/ngrokfindings are pre-existing and byte-identical between both images. (docker scoutwas unavailable — Docker Desktop is gone from the dev machine — trivy used as the scanner.)cixstack was temporarily switched to the test image — container healthy,/app/llama-serverresident with ~514 MiB VRAM innvidia-smicompute-apps (explicit GPU verification, no CPU fallback), semantic search returned ranked results (query embedding exercised end-to-end). Stack restored tov0.12.1-cu128afterwards.The digest reaches prod with the next
server/v*release;develop-cu128picks it up as soon as this merges.🤖 Generated with Claude Code