b10516
ggml-org/llama.cppb10516Aug 20, 2026by github-actions[bot]same day as b10514
What changed since b10514
Introduces Granite SWA models and fixes Vulkan crash
Improvements
- Improved Vulkan backend stability with null checks
Bug fixes
- Fixed potential crash in Vulkan backend queue cleanup
Upgrade notes
No configuration changes are required. Users with Vulkan enabled will benefit from a crash fix.
Analyzed Oct 20, 2026
Upgrading?
Release notes summary
Addresses a potential crash in the Vulkan backend by adding null checks in the queue command pools cleanup function.
Key Highlights
- Added null checks in ggml_vk_queue_command_pools_cleanup
- Improved Vulkan backend stability
New Features
- Vulkan null check fix
Release Notes (excerpt)
<details open> vulkan: add null checks in ggml_vk_queue_command_pools_cleanup (#27353) * Guard against null queue pointers. </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.com/ggml-org/llama.cpp/attestations/41873046> **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)…
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