b9816

ggml-org/llama.cppb9816Jun 26, 2026by github-actions[bot]same day as b9814

What changed since b9814

low risk

b9816 is a small housekeeping step over b9814, adding only a GGML upstream sync for thread safety and consistency.

Improvements

  • Synchronized the bundled GGML sources with upstream, improving thread safety and internal consistency across the library.
  • Build artifacts are regenerated for all platforms (macOS/iOS, Linux CPU/Vulkan/ROCm/OpenVINO/SYCL) with no packaging changes.

Upgrade notes

This is a routine GGML sync with no API, CLI, or config changes noted, so a drop-in replacement of the binaries or a rebuild should suffice. Because the sync touches threading internals, re-run your concurrency/throughput smoke tests if you rely on multi-threaded inference. No migration steps are required.

Analyzed Nov 1, 2026

Upgrading?

Release notes summary

GGML synchronization updates to improve thread safety and consistency across the library.

Key Highlights

  • GGML synchronization updates

New Features

  • GGML sync improvements

Release Notes (excerpt)

<details open> sync : ggml </details> **macOS/iOS:** - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED - macOS Intel (x64) - iOS XCFramework **Linux:** - Ubuntu x64 (CPU) - Ubuntu arm64 (CPU) - Ubuntu s390x (CPU) - Ubuntu x64 (Vulkan) - Ubuntu arm64 (Vulkan) - Ubuntu x64 (ROCm 7.2) - Ubuntu x64 (OpenVINO) - Ubuntu x64 (SYCL FP32) - Ubuntu x64 (SYCL FP16) **Android:** - Android arm64 (CPU) **Windows:** - Windows x64 (CPU) - Windows arm64 (CPU)…

Published by ggml-org on GitHub.

Read the full release notes

Related Repositories