Upgrade llama.cpp from b10034 to b10056#345
Merged
Merged
Conversation
Bump the pinned llama.cpp version four-file set: - llama/CMakeLists.txt: GIT_TAG + -DLLAMA_TAG b10034 -> b10056 - README.md: badge and release link - CLAUDE.md: pinned-version line + build-example clone tag + pin references - LlamaCppVersion.java: LLAMA_CPP_VERSION constant (+ javadoc examples; resolved commit example -> b10056-b85833e93) The b10034..b10056 range (22 commits, 89 files, ~397 KiB) is additive/tuning- only with no public-API surface change: all eight priority-8 headers are byte- identical. ggml.h only adds three DeepSeek-V4 hyper-connection op enums and ggml-cpu.h adds ggml_cpu_has_sme2() (additive, upstream-compiled). The three touched tools/server/* files are internal: server-common.h adds an inline has_media(); server-context.cpp re-gates slot save/restore/erase on slot media content (check_no_mtmd -> check_slot_no_media); server-http.cpp guards an empty CORS Origin header — none overlapping any patch region. The bulk is ggml backend kernel work (CUDA DSV4-HC, Arm SME2, a large Hexagon DSP rework, OpenCL/Vulkan) inside upstream-compiled TUs. Verified in-sandbox (Linux x86_64): fresh cmake configure applied all six patches (0001-0003, 0006-0008) fail-loud clean, the OuteTTS generator extracted tts.cpp @ b10056 (anchors held, ggml commit b85833e93), the full native build linked libjllama.so + jllama_test incl. the changed server TUs, and ctest was 485/485 green. Appended the breaking-changes history rows. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01VGyzjuEe3LzM1eFzs6ypJf
bernardladenthin
had a problem deploying
to
startgate
July 17, 2026 09:57 — with 
GitHub Actions
Error
bernardladenthin
had a problem deploying
to
maven-central
July 17, 2026 09:57 — with
GitHub Actions
Failure
bernardladenthin
had a problem deploying
to
maven-central
July 17, 2026 09:57 — with
GitHub Actions
Failure
|
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
b10034tob10056across all configuration files and documentationLlamaCppVersion.LLAMA_CPP_VERSIONconstant to reflect the new upstream versionGIT_TAGand TTS generator tag referencesTest plan
Related issues / PRs
Checklist
CONTRIBUTING.mdandCODE_OF_CONDUCT.mdSECURITY.md)https://claude.ai/code/session_01VGyzjuEe3LzM1eFzs6ypJf