Repository navigation
Upgrade llama.cpp from b11815 to b11827 - #556
Merged
Merged
Conversation
Five upstream commits (d77256999 = b11820). One compile break, in
jllama_engine.cpp: format_prompt_rerank() takes the decoded images
of the query and the document since #29625 ("server : support typed
content input for RERANK endpoint"); engine::rerank passes two empty
lists, which is the old text-only prompt.
The rerank route reads the query and each document as a string or
{"text": string or [strings], "image": ...} now. OaiRerankSupport
follows the text half: an object query is accepted, a text array
concatenated, and an item with an image is a 400 naming NativeServer
instead of being ranked by its text alone (an object document's
other keys used to be ignored); video/fps/max_frames get upstream's
message. Six new cases in OaiRerankSupportTest, red before the
change. readTopN's Javadoc says that upstream refuses a negative
top_n too now.
Also: Nemotron with a wider Q projection, the domyn-small pre-tokenizer
and a tokenizer.ggml.metaspace.prepend_scheme key (#23343);
posix_memalign in the Vulkan buffers (#30828); two CI-only commits.
All 12 patches apply unchanged (check-patches.py: 88 hunks,
0 problems). The drop-checks of 0002, 0003 and 0021, whose file
server-context.cpp is in the range, still find the defects. The server
request fields, their bounds and the response keys are identical.
Verified: fresh configure and build, ctest 686/686,
NativeLibraryLoadSmokeTest 7/7 against the b11820 library,
OaiRerankSupportTest 30/30, OpenAiCompatServerHttpTest 81/81, spotless
and spotbugs clean.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VBFFnrhtvXiUeyxjmUc4R2
Seven upstream commits (970b51ce7 = b11827), no source change here: SYCL multi-column mat-vec on the Intel XMX engines for short batches (#29864, GGML_SYCL_ENABLE_XMX_ESIMD), an OpenCL CONV_2D_DW kernel (#30900), the MiniCPM-OCR 1.0 projector in mtmd (#30979), DFlash drafter fixes for qwen4exp (#30927) and glm5-next (#30932), and --mlock locking the parts of a split host buffer (a CUDA pinned host buffer above 4 GB, skipped before). mtmd.h and mtmd-helper.h are not in the range, nor is anything in common/, include/ or tools/server/. All 12 patches apply unchanged (check-patches.py: 88 hunks, 0 problems); no patch-target file is in the range. Upstream's build files and .github/ are unchanged across b11815..b11827, so the toolchain pins of publish.yml stay. Verified: fresh configure and build, ctest 686/686, NativeLibraryLoadSmokeTest 7/7 against the b11827 library. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01VBFFnrhtvXiUeyxjmUc4R2
The review of the b11820/b11827 commits found that OaiRerankSupport.readItem refused an item whose "image" was null or [] and one without a "text". Upstream's parse_item ranks both by their text (an empty text for the second). An object document with "image": null was ranked here before 5108b4d, so for documents this was a regression of that commit. readItem now follows parse_item step by step: video/fps/max_frames refused, a text string or array of strings concatenated (missing or null is empty text, another type or a non-string element is upstream's message), a null or empty image ignored, an image of another type or a list starting with a non-string refused with upstream's message. A string image or a list of them stays the one deliberate difference: a 400 naming NativeServer instead of ranking the text alone. Five new cases in OaiRerankSupportTest, four of them red before the change; the existing text-array case now expects upstream's quoting. Docs: the CHANGELOG's b11827 sentence called the glm5-next commit a DFlash fix (it removes graph inputs, #30932); TODO.md named a jllama_completion that does not exist and data URIs where the raw prompt carries base64; the b11820 history row said three 400s were new where only the negative top_n is, missed one comment line upstream adds in handle_embeddings_impl, and left convert_hf_to_gguf_update.py out of the file list. Verified: OaiRerankSupportTest 35/35, OpenAiCompatServerHttpTest 81/81, spotless and spotbugs clean. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01VBFFnrhtvXiUeyxjmUc4R2
bernardladenthin
had a problem deploying
to
maven-central
October 22, 2026 21:05 — with 
GitHub Actions
Failure
GitHub Actions
Failure
bernardladenthin
had a problem deploying
to
startgate
October 22, 2026 21:05 — with
GitHub Actions
Error
GitHub Actions
Error
bernardladenthin
had a problem deploying
to
maven-central
October 22, 2026 21:05 — with
GitHub Actions
Failure
GitHub Actions
Failure
|
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
format_prompt_rerank()two new parameters (the decoded images of the query and the document).engine::reranknow passes empty lists, which builds the same text-only prompt as before. Upstream's rerank route also takes typed items now:{"text": ..., "image": ...}.NativeServerserves that route with images included.OpenAiCompatServer(OaiRerankSupport) handles the text part the way upstream does, and refuses animagewith a 400 that namesNativeServerrather than ranking the text alone.LlamaModel.rerankandjllama_rerankstay text-only; wiring multimodal rerank through them is a TODO.md entry. This step also brings Nemotron with a wider Q projection, thedomyn-smallpre-tokenizer, thetokenizer.ggml.metaspace.prepend_schemekey, andposix_memalignin the Vulkan buffers.CONV_2D_DW, the MiniCPM-OCR 1.0 projector, a DFlash fix for qwen4exp, fewer graph inputs for glm5-next, and--mlocknow also locks split host buffers.readItemnow follows upstream'sparse_itemstep by step. Anullor emptyimagecounts as no image; it was a 400 after 5108b4d. A missing ornulltextis empty text. This commit also corrects five wording errors in the bump docs.All 12 patches apply unchanged (
check-patches.py: 88 hunks, 0 problems). Range b11815..b11820 touchesserver-context.{cpp,h}, the file patches 0002, 0003 and 0021 change. Their drop-checks still find the bugs those patches fix, so the patches stay. Upstream's build files and.github/are unchanged across the range, so the toolchain pins inpublish.ymlstay as they are.Test plan
ctest686/686,NativeLibraryLoadSmokeTest7/7 against that step's libraryOaiRerankSupportTest35/35 (11 new cases, each one failing before its fix, except the case that pins the refusal of an image list),OpenAiCompatServerHttpTest81/81check-natives.py,check-shared-files.pyandcheck-patches.pyall pass/v1/rerankrow,readTopNJavadocRelated issues / PRs
Follows #555. Upstream: ggml-org/llama.cpp#29625, #23343, #30828, #29864, #30900, #30979, #30927, #30932.
Checklist
CONTRIBUTING.mdandCODE_OF_CONDUCT.mdGenerated by Claude Code