b10426

ggml-org/llama.cppb10426Aug 14, 2026by github-actions[bot]same day as b10425

What changed since b10425

low risk

b10425 adds SYCL performance optimization; b10426 enforces single-thread execution on WASI for compatibility.

New features

  • WASI single-thread enforcement for compatibility

Improvements

  • Ensures compatibility with WASI environments

Upgrade notes

WASI builds now enforce single-thread execution to ensure compatibility. No configuration changes are required for other platforms.

Analyzed Oct 16, 2026

Upgrading?

Release notes summary

The ggml library now forces single-thread execution on the WASI platform to ensure compatibility.

Key Highlights

  • ggml: Force single thread on wasi
  • Ensures compatibility with WASI environments
  • Standard builds for all supported platforms

Release Notes (excerpt)

<details open> ggml: force single thread on wasi (#25686) </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