b10423

ggml-org/llama.cppb10423Aug 13, 2026by github-actions[bot]same day as b10419

What changed since b10419

low risk

Ensures CPU parameters are consistently applied across all tools

New features

  • Consistent CPU parameter application across tools

Improvements

  • Standard distribution of binaries for all supported platforms
  • Includes UI and various backend builds

Upgrade notes

No specific configuration changes required; focus is on internal consistency.

Analyzed Oct 16, 2026

Upgrading?

Release notes summary

This release ensures that CPU parameters are consistently applied across all tools, maintaining configuration uniformity.

Key Highlights

  • Common: Apply CPU parameters across tools
  • Standard distribution of binaries for all supported platforms
  • Includes UI and various backend builds

Release Notes (excerpt)

<details open> common: apply CPU parameters across tools (#27026) </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 7.14)DISABLED - Ubuntu x64 (OpenVINO) - Ubuntu x64 (SYCL FP32) - Ubuntu x64 (SYCL FP16) **Android:**…

Published by ggml-org on GitHub.

Read the full release notes

Related Repositories