Upgrade llama.cpp from b10423 to b10456 - #394
Merged
Merged
Conversation
bernardladenthin
had a problem deploying
to
maven-central
August 17, 2026 13:08 — with
GitHub Actions
Failure
bernardladenthin
had a problem deploying
to
startgate
August 17, 2026 13:08 — with
GitHub Actions
Error
bernardladenthin
had a problem deploying
to
maven-central
August 17, 2026 13:08 — with
GitHub Actions
Failure
Review Summary✅ Code Quality: Excellent This is a well-executed version upgrade PR that demonstrates meticulous attention to the project's upgrade discipline: Verification Checklist — All Items Complete
Upstream API Analysis — Thorough & AccurateThe breaking-changes documentation is exceptionally comprehensive, covering all 8 intermediate tags and correctly identifying that:
Testing
DocumentationThe PR description and breaking-changes history provide exceptional detail — future maintainers have everything needed to understand the upgrade rationale and scope. Result: No issues found. This upgrade is clean and follows all established procedures. |
|
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Details
This upgrade spans 8 intermediate tags (b10423→b10430→b10436→b10441→b10447→b10448→b10454→b10455→b10456) and includes:
on_new_taskcallback signature changed andyield_to_queue()added, but only upstream'sserver-context.cppregisters this callback — no project source is affectedggml_ssm_scan()gained a trailingint64_t Kparameter, but it is only called inside llama.cpp's own translation unitsmtmd-image.handmodels/models.h(internal helpers) changed, but public headersmtmd.handmtmd-helper.hare byte-identical across the rangeOf the 22 upstream headers the project includes directly, only 3 changed:
tools/server/server-queue.h: Breaking callback signature change (inert — upstream's sole registrant)ggml/include/ggml.h:ggml_ssm_scan()parameter addition (inert — called only in upstream TUs)tools/mtmd/mtmd-helper-common.h:size_twidening (no signature change)All other included headers (
llama.h,common.h,chat.h,arg.h,mtmd.h,mtmd-helper.h,tools/server/*.h) are byte-identical b10423→b10456.Test plan
git applysucceeded at every intermediate tagcmake --build+ctest485/485 passingRelated issues / PRs
Upstream: llama.cpp #27041, #27133, #27018, #27034, #27071, #27103, #27099, #27075, #27130, #27056, #27176, #27160, #26953, #26623, #26653, #26185, #25686, #25268
Checklist
CONTRIBUTING.mdandCODE_OF_CONDUCT.mdhttps://claude.ai/code/session_01JYGrvcgi2cnh6gg8D24uC7