b10318

ggml-org/llama.cppb10318Aug 7, 2026by github-actions[bot]same day as b10313

What changed since b10313

low risk

b10318 is a routine ggml library sync with rebuilt binaries; no functional llama.cpp changes are documented versus b10313.

Improvements

  • ggml submodule synced to a newer revision, picking up upstream library-level changes not itemized in the notes.
  • Refreshed pre-built binaries across macOS, Linux, Windows, Android, and openEuler targets.
  • Ubuntu x64 OpenVINO 2026.2.1 build artifact is listed in the newer release's download set.

Upgrade notes

This is a sync-only release, so no config or API migration is expected; the LRU router scheduler from b10313 remains in place. If you depend on the KleidiAI-enabled macOS build, note it is still disabled in both releases. Rebuild or re-download binaries rather than assuming behavioral changes.

Analyzed Oct 30, 2026

Upgrading?

Release notes summary

A general sync release for the ggml library, providing pre-built binaries for a wide range of platforms including macOS, Linux, Windows, Android, and openEuler.

Key Highlights

  • Pre-built binaries available for macOS (Apple Silicon and Intel), Linux (various distros and backends), Windows (CPU, CUDA, Vulkan, etc.), and Android.
  • iOS XCFramework provided for Apple mobile devices.
  • Disabled builds for macOS with KleidiAI enabled and openEuler builds pending resolution of a specific pull request.

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