b10192

ggml-org/llama.cppb10192Jul 30, 2026by github-actions[bot]same day as b10189

What changed since b10189

low risk

b10192 is a routine ggml library sync with no user-facing changes noted beyond the prior M3 graph refactor.

Improvements

  • Synchronizes the bundled ggml library across components to keep internal code aligned with upstream.

Upgrade notes

This is a housekeeping sync of the ggml submodule, so no config or API changes are expected; the earlier M3 custom-op removal in b10189 is already reflected in stock operations. Rebuild from source if you vendor ggml directly to pick up the synchronized state. Standard binary drop-in replacement should suffice.

Analyzed Nov 1, 2026

Upgrading?

Release notes summary

A general synchronization commit for the ggml library, integrating changes across components.

Key Highlights

  • Library-wide synchronization

New Features

  • General library maintenance

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 7.2) - 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