Upgrade llama.cpp from b10064 to b10069#354
Merged
Merged
Conversation
The b10064...b10069 diff is additive/tuning-only (8 files, 5 commits): ggml-OpenCL MoE dp4a activation-tile tuning + Adreno MUL_MAT broadcast/ view_offs handling, plus internal llama-lib changes (llama-quant.cpp excludes the i32 ffn_gate_tid2eid routing table from quantization; models/dflash.cpp rotates the injected DFlash K/V cache). All eight priority-8 API headers are byte-identical; no common/arg.*, tools/server/*, or tools/tts/tts.cpp touched. A fresh cmake configure re-applied all six patches (0001-0003, 0006-0008) cleanly and the OuteTTS generator extracted tts.cpp @ b10069 with all anchors holding. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01BZVvaLwXnCDK3qyz2A3BHb
bernardladenthin
had a problem deploying
to
maven-central
July 20, 2026 16:11 — with 
GitHub Actions
Failure
GitHub Actions
Failure
bernardladenthin
had a problem deploying
to
maven-central
July 20, 2026 16:11 — with
GitHub Actions
Failure
GitHub Actions
Failure
bernardladenthin
had a problem deploying
to
startgate
July 20, 2026 16:11 — with
GitHub Actions
Error
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 versionTest plan
Related issues / PRs
Checklist
CONTRIBUTING.mdandCODE_OF_CONDUCT.mdSECURITY.md)Details
This upgrade touches only configuration and documentation:
llama/CMakeLists.txt): UpdatedGIT_TAGfromb10064tob10069in both the FetchContent declaration and the TTS generator scriptLlamaCppVersion.java): UpdatedLLAMA_CPP_VERSIONstring constant and javadoc examplesCLAUDE.md,README.md, and added verification notes todocs/history/llama-cpp-breaking-changes.mdThe upstream changes (b10064→b10069) are additive/tuning-only with no public-API surface changes. All six existing patches apply cleanly, and the OuteTTS generator anchor (
tools/tts/tts.cpp) remains untouched.https://claude.ai/code/session_01BZVvaLwXnCDK3qyz2A3BHb