b10082

ggml-org/llama.cppb10082Jul 22, 2026by github-actions[bot]same day as b10081

What changed since b10081

low risk

b10082 adds a one-time KleidiAI warning for unsupported weight types, building on b10081's draft sidecar fix.

New features

  • KleidiAI now emits a single warning when a weight type has no matching kernel, surfacing when acceleration falls back.

Improvements

  • Weight-loading debuggability improved by making missing KleidiAI kernel coverage visible to users.
  • Warning is emitted only once per weight type to avoid log spam.

Upgrade notes

This is a patch-level bump with no config or CLI changes; existing flags and model setups continue to work. The only observable difference is an extra one-time log line on KleidiAI-enabled builds when an unsupported weight type is encountered, which is informational and safe to ignore.

Analyzed Nov 1, 2026

Upgrading?

Release notes summary

Adds a warning that triggers once when a specific weight type has no available KleidiAI kernel, improving debuggability and user awareness of hardware acceleration limits.

Key Highlights

  • Warns once when KleidiAI kernel is missing for a weight type
  • Improves debuggability for weight loading

Release Notes (excerpt)

<details open> kleidiai : warn once when a weight type has no KleidiAI kernel (#25701) </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 7.2) - Ubuntu x64 (OpenVINO) - Ubuntu x64 (SYCL FP32) - Ubuntu x64 (SYCL FP16)…

Published by ggml-org on GitHub.

Read the full release notes

Related Repositories