b9698

ggml-org/llama.cppb9698Jun 18, 2026by github-actions[bot]same day as b9697

What changed since b9697

low risk

Self-update in the app is now restricted to builds produced by llama-install.sh; otherwise only a CI parsing fix differs.

Improvements

  • Self-update is now gated on how the app was built, limiting it to llama-install.sh installations.
  • Builds from other sources no longer attempt in-app self-updates, reducing unexpected binary replacement.

Bug fixes

  • Corrected the check-release message parsing logic in CI (carried over from b9697).

Upgrade notes

If you rely on in-app self-update, ensure the binary was installed via llama-install.sh; builds from tarballs or package managers will no longer self-update. No config or model format changes are involved, so upgrading is otherwise drop-in.

Analyzed Nov 1, 2026

Upgrading?

Release notes summary

A build release modifying self-update behavior to only work when built with llama-install.sh.

Key Highlights

  • Enable self-update only when built with llama-install.sh
  • Signed-off-by: Adrien Gallouët

Release Notes (excerpt)

<details open> app : enable self-update only when built with llama-install.sh (#24754) Signed-off-by: Adrien Gallouët <angt@huggingface.co> </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)…

Published by ggml-org on GitHub.

Read the full release notes

Related Repositories