b10224
ggml-org/llama.cppb10224Aug 2, 2026by github-actions[bot]same day as b10223
What changed since b10223
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 notesRelated Repositories
:electron: Build cross-platform desktop apps with JavaScript, HTML, and CSS
Godot Engine – Multi-platform 2D and 3D game engine
ClickHouse® is a real-time analytics database management system
Self-hosted game stream host for Moonlight.
DuckDB is a high-performance analytical database system