Upgrade llama.cpp from b10069 to b10076#356
Merged
Merged
Conversation
Bumps the pinned llama.cpp release across all four required files (llama/CMakeLists.txt GIT_TAG + LLAMA_TAG, README badge/link, the CLAUDE.md pinned-version line and its consistency references, and the LlamaCppVersion.LLAMA_CPP_VERSION constant + Javadoc), and appends the upgrade-range rows to docs/history/llama-cpp-breaking-changes.md. The b10069...b10075 diff touches only the Qualcomm Hexagon DSP backend (new GGML_OP_CLAMP), the internal DSV4 KV-cache serializer, and the Svelte WebUI — no public-API surface. All eight priority-8 headers are byte-identical; common/arg.*, tools/server/*, and tools/tts/tts.cpp are unchanged, so all six patches (0001-0003, 0006-0008) apply cleanly and the OuteTTS build-time generator anchors hold. Verified locally: fresh cmake configure (patches applied fail-loud, TTS extracted from tts.cpp @ b10075), native jllama + jllama_test built clean, ctest 485/485 passing. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01EHY6D6rLhfWFNua1damGPd
Bumps the pinned llama.cpp release across all four required files (llama/CMakeLists.txt GIT_TAG + LLAMA_TAG, README badge/link, the CLAUDE.md pinned-version line and its consistency references, and the LlamaCppVersion.LLAMA_CPP_VERSION constant + Javadoc), and appends the upgrade-range rows to docs/history/llama-cpp-breaking-changes.md. The b10075...b10076 diff is a single file — ggml/src/ggml-cuda/getrows.cu, an int4-vectorized get_rows CUDA kernel refactor with a scalar fallback. No public-API surface; all eight priority-8 headers are byte-identical; common/arg.*, tools/server/*, and tools/tts/tts.cpp are unchanged, so all six patches (0001-0003, 0006-0008) apply cleanly and the OuteTTS generator anchors hold. Verified locally: fresh cmake configure (patches applied fail-loud, TTS extracted from tts.cpp @ b10076), native jllama + jllama_test built clean, ctest 485/485 passing. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01EHY6D6rLhfWFNua1damGPd
bernardladenthin
had a problem deploying
to
maven-central
July 21, 2026 19:19 — with 
GitHub Actions
Failure
bernardladenthin
had a problem deploying
to
maven-central
July 21, 2026 19:19 — with
GitHub Actions
Failure
bernardladenthin
had a problem deploying
to
startgate
July 21, 2026 19:19 — with
GitHub Actions
Error
|
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
LlamaCppVersion.LLAMA_CPP_VERSIONconstant to reflect the new upstream releaseDetails
The b10069→b10076 range includes:
getrows.cukernel optimization (loop-invariant hoisting + int4-vectorized path) — performance-only, no public-API surfaceAll six patches (
0001–0003,0006–0008) apply cleanly; all eight priority-8 headers remain byte-identical; nocommon/arg.*,tools/server/*, ortools/tts/tts.cpptouched.Test plan
ctestconfirmation)Related issues / PRs
Checklist
CONTRIBUTING.mdandCODE_OF_CONDUCT.mdhttps://claude.ai/code/session_01EHY6D6rLhfWFNua1damGPd