b10063

ggml-org/llama.cppb10063Jul 17, 2026by github-actions[bot]same day as b10061

What changed since b10061

medium risk

Synced the underlying ggml library to improve backend support and stability.

New features

  • Added support for SYCL backend.
  • Added support for HIP backend.
  • Added support for OpenVINO backend.

Improvements

  • Synced ggml library for general updates.
  • Expanded backend support across platforms.

Upgrade notes

No specific configuration changes are required. The underlying library sync may introduce subtle performance changes or behavioral differences depending on the selected backend.

Analyzed Oct 16, 2026

Upgrading?

Release notes summary

General sync release for ggml library updates across multiple platforms.

Key Highlights

  • Sync ggml library
  • macOS/iOS, Linux, Windows, Android, and openEuler builds available
  • Support for multiple backends including CUDA, Vulkan, ROCm, OpenVINO, SYCL, and HIP

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