b9990

ggml-org/llama.cppb9990Jul 13, 2026by github-actions[bot]same day as b9988

What changed since b9988

low risk

Added Minimax2 EAGLE3 speculative decoding support and fixed a crash in its implementation.

New features

  • Added Minimax2 EAGLE3 speculative decoding support

Bug fixes

  • Fixed nullptr crash in minimax2 EAGLE3 implementation

Upgrade notes

No configuration changes are required. Ensure the updated binary supports the new Minimax2 EAGLE3 model architecture.

Analyzed Oct 17, 2026

Upgrading?

Release notes summary

Added support for the Minimax2 EAGLE3 speculative decoding model, including a fix for a null pointer issue. This allows users to leverage faster inference speeds through speculative decoding with this specific model architecture.

Key Highlights

  • Added Minimax2 EAGLE3 support
  • Fixed nullptr crash in minimax2 EAGLE3 implementation
  • Enables speculative decoding for Minimax2 models

Release Notes (excerpt)

<details open> spec: add Minimax2 eagle3 support * Fix nullptr in minimax2 EAGLE3 * minor : add newline --------- Co-authored-by: Georgi Gerganov <ggerganov@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