b10224

ggml-org/llama.cppb10224Aug 2, 2026by github-actions[bot]same day as b10223

What changed since b10223

low risk

b10224 adds F16 repeat support to the WebGPU backend, a small feature delta over b10223's CI-only fixes.

New features

  • WebGPU backend now supports F16 (half-precision) repeat operations, improving web-context performance.

Improvements

  • WebGPU repeat handling extended to half-precision tensors, reducing fallback work in browser-based inference.

Upgrade notes

This is a routine build bump with no config or API changes; existing flags, model files, and scripts continue to work. WebGPU users may see slightly better performance on repeat-heavy graphs, while CPU/CUDA/ROCm/Vulkan paths are unaffected. No migration steps are required.

Analyzed Oct 31, 2026

Upgrading?

Release notes summary

Adds support for F16 (half-precision) repetition operations to the WebGPU backend.

Key Highlights

  • WebGPU backend F16 repeat support
  • Enhanced web context performance

Release Notes (excerpt)

<details open> ggml-webgpu: add support for f16 repeat (#26307) </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:**…

Published by ggml-org on GitHub.

Read the full release notes

Related Repositories