b10084

ggml-org/llama.cppb10084Jul 22, 2026by github-actions[bot]same day as b10083

What changed since b10083

low risk

b10084 adds a Hexagon DSP safety check that validates tensor types before reusing descriptors.

New features

  • Hexagon backend now verifies tensor type before reusing an existing descriptor.

Improvements

  • Descriptor reuse on the Hexagon backend is guarded against mismatched tensor configurations, reducing the chance of runtime errors or crashes.

Bug fixes

  • Prevents faults caused by reusing a Hexagon descriptor that was created for a different tensor type.

Upgrade notes

This is a single-commit increment over b10083 with no CLI, config, or API changes; only Hexagon/DSP users are affected. Standard binary swap is sufficient, and no model or cache migration is needed.

Analyzed Nov 1, 2026

Upgrading?

Release notes summary

Adds a safety check for tensor types when reusing Hexagon (DSP) descriptors to prevent errors or crashes associated with mismatched tensor configurations.

Key Highlights

  • Hexagon tensor type check before reusing descriptors
  • Prevents potential errors in DSP tensor management

Release Notes (excerpt)

<details open> hexagon: check tensor type when reusing descriptors (#25968) </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) **Android:**…

Published by ggml-org on GitHub.

Read the full release notes

Related Repositories