b9959

ggml-org/llama.cppb9959Jul 11, 2026by github-actions[bot]same day as b9957

What changed since b9957

low risk

b9959 is a housekeeping release that only syncs the internal ggml library; no user-facing changes are documented.

Improvements

  • Synchronizes the bundled ggml core with upstream, picking up internal library updates.
  • Rebuilt release binaries for all existing platforms (macOS, Linux CPU/Vulkan/ROCm/OpenVINO/SYCL) against the synced ggml.

Upgrade notes

This is a routine ggml sync with no documented API, config, or CLI changes, so upgrading from b9957 should be a drop-in binary swap. Re-validate any custom builds or patches against the synced ggml submodule, since its internal changes are not itemized in the notes.

Analyzed Oct 24, 2026

Upgrading?

Release notes summary

Syncs and updates the ggml library core.

Key Highlights

  • Internal ggml synchronization

New Features

  • Internal ggml updates

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