b10284
ggml-org/llama.cppb10284Aug 5, 2026by github-actions[bot]same day as b10282
What changed since b10282
Patch release b10284 fixes a memory allocation bug in MTP (Multi-Token Prediction) layers.
Bug fixes
- Corrected memory allocation for MTP layers, which previously could cause crashes or memory corruption.
Upgrade notes
This is a two-build patch bump with no configuration or API changes, so it can be dropped in place of b10282. Users running models with Multi-Token Prediction layers should upgrade to avoid the allocation fault. No migration steps are required.
Analyzed Oct 31, 2026
Upgrading?
Release notes summary
Fixes a memory allocation bug affecting MTP layers (Multi-Token Prediction).
Key Highlights
- Fixes memory allocation for MTP layers
- Prevents potential crashes or memory corruption
Release Notes (excerpt)
<details open> fit: Fix memory allocation for MTP layers (#26605) </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 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