b9771
ggml-org/llama.cppb9771Jun 23, 2026by github-actions[bot]same day as b9770
What changed since b9770
Optimizes Vulkan shaders to reduce binary size via specialization constants.
New features
- Vulkan shader optimization to reduce binary size
Improvements
- Vulkan binary size reduction via specialization constants
Upgrade notes
No configuration changes are required for this release.
Analyzed Oct 17, 2026
Upgrading?
Release notes summary
This release optimizes Vulkan shader variants by converting the ALIGNED flag for matrix multiplication into a specialization constant, which reduces binary size.
Key Highlights
- Make mul_mm ALIGNED a spec constant to trim shader variants and reduce binary size
- macOS/iOS binaries
- Linux binaries
- Windows binaries
Release Notes (excerpt)
<details open> vulkan: make mul_mm ALIGNED a spec constant (#24689) This trims down some of the shader variant explosion and reduces binary size. </details> **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)…
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