b9773
ggml-org/llama.cppb9773Jun 23, 2026by github-actions[bot]same day as b9771
What changed since b9771
Adds GET_ROWS_BACK support to Vulkan backend and shrinks binary size via specialization constants
New features
- Support for GET_ROWS_BACK operation in Vulkan backend
Improvements
- Converted mul_mm ALIGNED to specialization constant to reduce Vulkan binary size
Upgrade notes
No configuration changes required; simply update the binaries.
Analyzed Oct 17, 2026
Upgrading?
Release notes summary
This release adds support for the GET_ROWS_BACK operation in the Vulkan backend.
Key Highlights
- Support GET_ROWS_BACK in Vulkan backend
- macOS/iOS binaries
- Linux binaries
- Windows binaries
Release Notes (excerpt)
<details open> vulkan: Support GET_ROWS_BACK (#24883) </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) - Ubuntu x64 (SYCL FP16) **Android:** - Android arm64 (CPU) **Windows:** - Windows x64 (CPU)…
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