b10002

ggml-org/llama.cppb10002Jul 14, 2026by github-actions[bot]same day as b10001

What changed since b10001

medium risk

b10002 adds ggml helper functions for checking contiguity of inner tensor dimensions, with no other functional changes.

New features

  • New ggml utility functions to test whether inner tensor dimensions are contiguous.

Improvements

  • Additive ggml API surface that lets callers validate tensor layout assumptions before running ops.

Upgrade notes

This is a purely additive change on top of b10001, so existing binaries and callers need no modification. If you build against ggml directly, the new contiguity helpers are available for use but nothing is deprecated or removed. No config or model migration is required.

Analyzed Oct 30, 2026

Upgrading?

Release notes summary

Adds a set of utility functions to check the contiguity of inner tensor dimensions and releases standard binaries for supported platforms.

Key Highlights

  • Added functions for checking contiguity of inner tensor dimensions.
  • Released standard build binaries for macOS, Linux, Android, Windows, and openEuler.

Release Notes (excerpt)

<details open> ggml : add a set of functions for checking contiguity of inner tensor dimensions (#25650) Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com> </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)…

Published by ggml-org on GitHub.

Read the full release notes

Related Repositories