b10059
ggml-org/llama.cppb10059Jul 17, 2026by github-actions[bot]same day as b10058
What changed since b10058
Default Hadamard matrix multiplication implementation switched to CPU routine.
Improvements
- Default Hadamard mul_mat implementation switched to CPU routine for stability or performance
Upgrade notes
No configuration changes are required. Users may notice slight performance variations depending on their hardware.
Analyzed Oct 16, 2026
Upgrading?
Release notes summary
Changes the default implementation for Hadamard matrix multiplication to use a CPU routine.
Key Highlights
- Default Hadamard mul_mat moved to CPU routine
- Likely adjustment for performance or stability
New Features
- CPU default for Hadamard mul_mat
Release Notes (excerpt)
<details open> ggml-blas: default hadamard mul_mat to cpu routine (#25710) Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> </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)…
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