b10516

ggml-org/llama.cppb10516Aug 20, 2026by github-actions[bot]same day as b10514

What changed since b10514

low risk

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 notes

Related Repositories