b10223

ggml-org/llama.cppb10223Aug 1, 2026by github-actions[bot]same day as b10221

What changed since b10221

low risk

Only CI test fixes between b10221 and b10223; no runtime or API changes for users.

Improvements

  • Continuous integration pipeline errors were corrected, improving build and test reliability for contributors.
  • Test suite stability was tightened, reducing spurious CI failures.

Bug fixes

  • Resolved several CI failures introduced by earlier test changes.

Upgrade notes

This delta touches only the test/CI layer, so no configuration, model, or API migration is required. Existing binaries and command-line flags from b10221 remain valid. Rebuilding is optional unless you depend on CI artifacts.

Analyzed Nov 1, 2026

Upgrading?

Release notes summary

Fixes errors in the Continuous Integration pipeline to ensure build stability.

Key Highlights

  • CI pipeline error fixes
  • Test suite stability improvements

New Features

  • CI/CD improvements

Release Notes (excerpt)

<details open> test: fix some CI errors (#26415) </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)…

Published by ggml-org on GitHub.

Read the full release notes

Related Repositories