b9687

ggml-org/llama.cppb9687Jun 17, 2026by github-actions[bot]same day as b9686

What changed since b9686

low risk

b9687 relaxes main_gpu validation so it is skipped when no devices are present, avoiding spurious config errors.

New features

  • main_gpu validation is now conditional, allowing configurations with zero detected devices to pass initialization.

Improvements

  • Improved handling of empty device scenarios by bypassing main_gpu checks when no devices are available.

Bug fixes

  • Prevents erroneous main_gpu validation failures in environments where no compute devices are enumerated.

Upgrade notes

This is a one-commit patch on top of b9686; no config or API changes are required. Users running CPU-only or device-less setups may see startup validation errors disappear. Otherwise behavior is unchanged.

Analyzed Oct 31, 2026

Upgrading?

Release notes summary

Modifies validation logic to skip main GPU configuration checks when no devices are available, improving handling of empty device scenarios.

Key Highlights

  • Skip main_gpu validation logic
  • Improved device availability handling

Release Notes (excerpt)

<details open> llama : skip main_gpu validation when no devices are available (#23405) </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)…

Published by ggml-org on GitHub.

Read the full release notes

Related Repositories