Conversation
Bump the wrapped llama.cpp server images from upstream build b9265 to b9404 (highest build with all four variants — generic, cuda, rocm, vulkan — published on ghcr.io; the latest GitHub release b9410 has no images published yet). npm update refreshed transitive deps; @start9labs/start-sdk stays at 1.5.3 (already latest).
MattDHill
previously approved these changes
May 29, 2026
The rocm variant exhausts runner disk (no space left on device) while pulling the GPU image. Enable the shared-workflow disk-cleanup step, as the comparably large ollama package already does.
MattDHill
approved these changes
May 29, 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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
llama-serverimages from upstream build b9265 → b9404 (upstreamBuildinstartos/manifest/index.ts). All four variants —generic,nvidia(cuda),rocm,vulkan— are published for b9404 onghcr.io/ggml-org/llama.cppand bump together.1.0.9265:0 → 1.0.9404:0, with one-line release notes in all five locales (startos/versions/current.ts).npm updaterefreshed transitive deps.@start9labs/start-sdkis unchanged at 1.5.3 (already the latest on npm), so no SDK bump and no migration.Notes
ghcr.ioyet. PerUPDATING.md, b9404 is the highest build with all four variants resolving, so that's the target.--host,--port,--api-key, and-hf/--hf-filevia the model presets) are core, stablellama-serverflags — unchanged across the b9265→b9404 range, so the presets instartos/actions/presets.tsremain valid. No breaking flag/server-API changes apply.README.mdandinstructions.mdneed no edits (neither references a version/build number).Test plan
npm run check(tsc) is green.make generic(and ideally all four variants) builds the.s9pk— verified in review per the monitor cycle.