b9628

ggml-org/llama.cppb9628Jun 14, 2026by github-actions[bot]same day as b9627

What changed since b9627

low risk

b9628 is a housekeeping release that only adds SYCL to the release-check tooling, with no runtime or API changes over b9627.

Improvements

  • Release-check scripts now include SYCL, improving build coverage consistency across platforms.
  • All platform binaries were rebuilt for the new tag, including the SYCL FP32 Linux artifact.

Upgrade notes

This is effectively a no-op for users: the only change is in CI/release verification scripts, so no config or migration work is needed. The llama-ui-embed crash fix from b9627 is already included and carries forward. Binaries are simply rebuilt under the new tag.

Analyzed Nov 1, 2026

Upgrading?

Release notes summary

Added SYCL (ComputeCpp) support to the release check scripts to ensure consistency across builds.

Key Highlights

  • Added SYCL to check-release process
  • Updated binaries for all platforms

Release Notes (excerpt)

<details open> add sycl to check-release (#24583) </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)…

Published by ggml-org on GitHub.

Read the full release notes

Related Repositories