Upgrade llama.cpp from b11214 to b11222 - #460
Merged
Merged
Conversation
Eight upstream commits. #29537 moved the "initializing ..." log in llama_server() below the common_params_parse call, which is the context of the parse-call hunk in patches 0001 and 0006; both hunks were re-anchored, content unchanged, and all eight patches apply in order on b11222. 0001 is still required (no common_params_parse_main upstream, the _WIN32 argv override is still there). No project source change: #29518 (string_split<T> throws on an unparsable element) only affects the numeric benchmark options, and #29537's always-registered --rpc is not used by ModelOption. No release.yml change upstream, so the CUDA/ROCm/OpenVINO pins stay. 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 18:57 — with
GitHub Actions
Failure
bernardladenthin
had a problem deploying
to
maven-central
September 27, 2026 18:57 — with
GitHub Actions
Failure
bernardladenthin
had a problem deploying
to
startgate
September 27, 2026 18:57 — with
GitHub Actions
Error
|
This was referenced Sep 27, 2026
This branch had an error being 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
b11214tob11222(eight upstream commits). The pin is updated inllama/CMakeLists.txt, the README badge,CLAUDE.mdandLlamaCppVersion.CHANGELOG.mdanddocs/history/llama-cpp-breaking-changes.mdget entries.0001and0006refreshed, content unchanged. Upstream #29537 movedSRV_INF("initializing ...")below thecommon_params_parsecall inllama_server(). That line was the context of both patches' parse-call hunk. The hunks now anchor on the precedingserver_stream_session_manager_start()lines. All eight patches apply in order on pristine b11222.0001: still required.b11222:common/arg.hhas nocommon_params_parse_main, and the_WIN32argv = utf8.ptrs.data()override is still incommon/arg.cpp.string_split<T>now throws on a token it cannot parse. The only numeric callers are the benchmark options-npp/-ntg/-npl.--rpcis now always registered and errors out in builds without RPC. This project builds withGGML_RPC=OFF, and--rpcis not inModelOption.dictbuiltin, conversion scripts, upstream CI) arrives automatically.release.ymlis unchanged, so the CUDA/ROCm/OpenVINO pins stay.Test plan
git applyin filename order on pristine b11222Related issues / PRs
Follows #458 (b11211 → b11214).
Checklist
CONTRIBUTING.mdandCODE_OF_CONDUCT.md🤖 Generated with Claude Code
https://claude.ai/code/session_01QSXAwbXqx9u5xsMArMvgT8
Generated by Claude Code