b9697

ggml-org/llama.cppb9697Jun 18, 2026by github-actions[bot]same day as b9694

What changed since b9694

low risk

CI-only release fixing check-release message parsing; no runtime or API changes between b9694 and b9697.

Improvements

  • CI release-check workflow now parses release messages correctly, improving release automation reliability.
  • Build artifacts remain the same set across platforms, with macOS KleidiAI still disabled as in the prior release.

Bug fixes

  • Fixed the check-release message parsing logic in the CI pipeline (PR #24751).

Upgrade notes

This is a CI/build-infrastructure-only delta, so no application code, CLI flags, or model formats changed. Upgrading from b9694 to b9697 should be a drop-in replacement with no config or migration steps. If you pinned b9694, you can safely move to b9697 for identical runtime behavior.

Analyzed Nov 1, 2026

Upgrading?

Release notes summary

A build release fixing the check-release message parsing logic.

Key Highlights

  • Fixed check-release message parsing

Release Notes (excerpt)

<details open> ci : fix check-release message parsing (#24751) </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:**…

Published by ggml-org on GitHub.

Read the full release notes

Related Repositories