b10430

ggml-org/llama.cppb10430Aug 14, 2026by github-actions[bot]same day as b10429

What changed since b10429

low risk

b10430 adds support for virtual integrated GPU devices, a small additive change over b10429's server monitoring access.

New features

  • llama.cpp can now target virtual iGPU devices, broadening the set of hardware configurations that can be used for inference.

Improvements

  • Documentation around the new device handling path was clarified with improved comments.
  • Existing backends remain compatible, so the change is purely additive to device selection logic.

Upgrade notes

This is a single-commit build bump with no config or API changes required; existing launch flags and backends continue to work as before. Only users running on virtualized or passthrough iGPU setups need to do anything, and even they should see no behavioral change unless they explicitly select such a device.

Analyzed Oct 24, 2026

Upgrading?

Release notes summary

This release adds support for virtual integrated GPU devices in llama.cpp, expanding hardware compatibility options for various platforms.

Key Highlights

  • Added support for virtual igpu devices
  • Improved comment documentation
  • Maintained compatibility with all existing backends

Release Notes (excerpt)

<details open> llama : allow virtual igpu devices (#26953) * llama : allow virtual igpu devices * cont : better comment </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 7.14)DISABLED - Ubuntu x64 (OpenVINO)…

Published by ggml-org on GitHub.

Read the full release notes

Related Repositories