Upgrade llama.cpp from b11211 to b11214 - #458
Merged
Merged
Conversation
Three upstream commits (HIP fattn-mma on CDNA, Vulkan argsort for Adreno, and #29516: an llguidance grammar without llguidance now throws instead of GGML_ABORT, so it no longer kills the JVM). No API or workflow change; all eight patches apply unchanged. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01QSXAwbXqx9u5xsMArMvgT8
bernardladenthin
had a problem deploying
to
maven-central
September 27, 2026 12:58 — with 
GitHub Actions
Failure
GitHub Actions
Failure
bernardladenthin
had a problem deploying
to
startgate
September 27, 2026 12:58 — with
GitHub Actions
Error
GitHub Actions
Error
bernardladenthin
requested a deployment
to
maven-central
September 27, 2026 12:58 — with
GitHub Actions
Waiting
GitHub Actions
Waiting
|
This was referenced Sep 27, 2026
This branch is waiting to be deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Three upstream commits (5 files, 29 lines). From this project's side the bump only changes the version; none of the three needs code changes here.
dkq > 256at large batch sizes.common_sampler_initnow throws (failed to parse grammar: llguidance is not enabled) instead of callingGGML_ABORTwhen an llguidance grammar reaches a build without llguidance. These builds do not enable llguidance, so such a grammar used to abort the whole JVM; it now fails the request instead.Upstream changed no API, workflow, ROCm version or CUDA component list in this range. All eight local patches apply unchanged.
Files changed:
CLAUDE.mdlists:llama/CMakeLists.txt,README.md,CLAUDE.mdandLlamaCppVersion.java.CHANGELOG.md.docs/history/llama-cpp-breaking-changes.md.Test plan
2ebd9ae62, which isb11214.jllama+jllama_test) passes, andctestpasses 559/559.Related issues / PRs
Follows #456 (b11211) and #457.
🤖 Generated with Claude Code
https://claude.ai/code/session_01QSXAwbXqx9u5xsMArMvgT8
Generated by Claude Code