b9930
ggml-org/llama.cppb9930Jul 8, 2026by github-actions[bot]same day as b9929
What changed since b9929
b9930 is a single-fix release correcting llama-batch handling of decreasing positions within a sequence.
Bug fixes
- llama-batch now correctly permits positions to decrease within a sequence instead of rejecting them.
Upgrade notes
This is a one-commit patch over b9929 with no API, config, or build changes; binaries are simply rebuilt across all platforms. Upgrade if you rely on batch sequences with non-monotonic positions, otherwise the delta is negligible.
Analyzed Oct 30, 2026
Upgrading?
Release notes summary
Fixes a bug in the llama-batch system allowing positions to decrease within a sequence.
Key Highlights
- Fixed allowed decreasing position in a sequence
- Updated binaries for macOS, iOS, Linux, Windows, and Android
Release Notes (excerpt)
<details open> llama-batch: fix allowed decreasing pos in a seq (#25449) </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) **Windows:**…
Published by ggml-org on GitHub.
Read the full release notesRelated Repositories
:electron: Build cross-platform desktop apps with JavaScript, HTML, and CSS
Godot Engine – Multi-platform 2D and 3D game engine
ClickHouse® is a real-time analytics database management system
Self-hosted game stream host for Moonlight.
DuckDB is a high-performance analytical database system