Skip to content

Upgrade llama.cpp from b12283 to b12289 - #613

Merged
bernardladenthin merged 2 commits into
mainfrom
claude/wonderful-tesla-1fkezz
Nov 11, 2026
Merged

bernardladenthin merged 2 commits into
mainfrom
claude/wonderful-tesla-1fkezz

Conversation

@bernardladenthin

Copy link
Copy Markdown
Owner

Summary

  • Pins llama.cpp b12289 (03d6c824e1ccbdb8e45b82299b1965cf94c5c056), six upstream commits after b12283. They touch only ggml/src/ggml-cuda/*, ggml/CMakeLists.txt, ggml/cmake/common.cmake, upstream's tests/ and two WebUI files: an FP8 E4M3 KV cache on CUDA, and ggml-cuda now links CUDA::cublasLt. No file a local patch touches changed; all 20 patches apply unchanged, and the WebUI lockfile is unchanged.
  • The tiny-model generator can write the per-layer KV cache scales (blk.N.attn_k.k_scale, attn_v.v_scale) an 8-bit float cache divides K and V by, and two CApiFp8Cache tests use them: a model with scales answers with f8_e4m3 on both sides and on one, with flash attention on and off, the same from a saved and restored slot, and under an F16 cache exactly like the model without scales; a scale of zero fails the load with the 8-bit float cache only. No test reached that path before.
  • README, CLAUDE.md, CHANGELOG, TODO.md, docs/history/llama-cpp-breaking-changes.md, LlamaCppVersion and the natives NOTICE follow the pin.

Test plan

  • C++ suite locally (Linux x86-64, CPU, static build against b12289 with the patches applied): 776/776 ctest cases, 732 test definitions
  • NativeLibraryLoadSmokeTest, LlamaCppVersionTest; check-natives.py, check-patches.py, the buildcheck unit tests
  • CI is green on this branch
  • Docs / CHANGELOG updated

Not measured: the CUDA side of the bump (the FP8 cache kernels, the cublasLt link) -- no GPU here or on the runners; the two CUDA module jobs build it. A CUDA consumer now needs cublasLt64_13.dll / libcublasLt.so.13 from the toolkit, which the README already lists for Windows.

Related issues / PRs

Follows #612.

Checklist

  • I have read CONTRIBUTING.md and CODE_OF_CONDUCT.md
  • My commits follow Conventional Commits
  • No security-sensitive changes

Generated by Claude Code

Six upstream commits: OCP FP8 E4M3 and new flash-attention cases in the CUDA
module, MMVF for BF16, upstream's tests, two WebUI components. No header this
library includes moved; all 20 patches apply unchanged.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01S8cAMZXymmPba3YZr2YCWp
The generator writes the per-layer k_scale / v_scale tensors; the model answers
with f8_e4m3 on both sides and on one, with flash attention on and off, the same
from a restored slot, and under F16 like the model without scales. A scale of
zero fails the load with the 8-bit float cache only. 732 tests, 776 cases.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01S8cAMZXymmPba3YZr2YCWp
@coderabbitai

coderabbitai Bot commented Nov 11, 2026 •

Copy link
Copy Markdown

Explain Change →

Caution

Review failed

The pull request is closed.

  • Autofix · Keep fixing CodeRabbit findings and required CI, and resolving merge conflicts

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

Share

Copy link
Copy Markdown
Owner Author

claude-review is red and is not this PR's: the action ends 18 s in with Claude execution failed: result is_error:true, before it reads the diff, exactly as on main and on #612. It is the review workflow's own run (its Claude call fails), not code in this change; no fix for it exists in the repository, and I cannot re-run it from here. The same holds for submit-maven and FOSSA's "License Compliance" should they report red here as they do on main. Everything else on this PR I watch and fix.


Generated by Claude Code

@bernardladenthin
bernardladenthin merged commit f9f0fc1 into main Nov 11, 2026
17 of 54 checks passed
@bernardladenthin
bernardladenthin deleted the claude/wonderful-tesla-1fkezz branch November 11, 2026 21:08
@sonarqubecloud

Copy link
Copy Markdown

This branch was successfully deployed

1 active deployment
startgate — 86974649 Deployed Nov 11, 2026 by bernardladenthin via Start gate (abort window) #1496
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants