b10485

ggml-org/llama.cppb10485Aug 18, 2026by github-actions[bot]same day as b10483

What changed since b10483

low risk

Delta is a routine upstream ggml core sync; no user-facing changes beyond the prior build-system cleanup.

Improvements

  • Core ggml library code resynchronized with the upstream ggml repository.
  • Build-system cleanup from the previous release (xcframework fix, vendor:: alias targets) carries forward.

Upgrade notes

This is a source-sync release with no documented API or config changes, so a drop-in rebuild should suffice. If you build from source, do a clean CMake reconfigure to pick up the vendored-library alias targets introduced just before this release. No migration steps are required.

Analyzed Oct 24, 2026

Upgrading?

Release notes summary

Synchronizes core ggml library code with the main repository, incorporating necessary updates from the upstream source.

Key Highlights

  • Core ggml library synchronization
  • Update ggml core components

New Features

  • Core ggml library updates

Release Notes (excerpt)

<details open> sync : ggml </details> **Website:** - <https://llama.app> **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 7.14)DISABLED - Ubuntu x64 (OpenVINO) - Ubuntu x64 (SYCL FP32) - Ubuntu x64 (SYCL FP16) **Android:** - Android arm64 (CPU) **Windows:**…

Published by ggml-org on GitHub.

Read the full release notes

Related Repositories