Models & Labs
llama.cpp b9180 Release Enhances MTP Support
llama.cpp Releaseshigh confidence
Why it matters
- →Enhances MTP support, making it more robust and versatile.
- →Introduces partial sequence rollback, optimizing speculative decoding.
- →Improves efficiency and adaptability for developers using complex AI models.
The b9180 release of llama.cpp focuses on enhancing MTP support, with improvements like fixing batch sizes and simplifying the codebase. It introduces partial sequence rollback for GDN models, optimizing speculative decoding by minimizing checkpoint restarts. This update makes llama.cpp more efficient and adaptable for developers using complex AI models across different platforms, including macOS, Linux, and Windows.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
What happened next
- 1llama.cpp b9200 Release Enhances Performance
llama.cpp Releases · May 18, 2026 · Same story
- 2llama.cpp b10593 Release Fixes and Enhancements
llama.cpp Releases · August 24, 2026 · Same story
More from llama.cpp Releases
Coding Toolscoding
llama.cpp b12022 adds ROCm 10 and Snapdragon support
This release quietly cements llama.cpp as the universal inference runtime by finally bringing ROCm 10.0 to Linux and Windows alongside CUDA 13.4, effectively closing the hardware gap for AMD users who were previously left behind. The inclusion of native Snapdragon support on Linux marks a significant step toward running local LLMs on ARM-based mobile chips without emulation overhead. While KleidiAI on Apple Silicon is disabled in this build, the broader expansion to diverse accelerators ensures that developers aren't locked into NVIDIA ecosystems anymore.
llama.cpp Releases
Coding Toolscoding
llama.cpp b12023 fixes shared prefix bug
This release addresses a specific inference artifact where decision prefixes were incorrectly bleeding into output embeddings. By capping shared prefixes at the first output position, llama.cpp ensures that option tokens remain distinct for parent and child tasks. This is a targeted fix for multi-step reasoning or voting workflows rather than a performance boost. It stabilizes complex generation patterns without changing the underlying model architecture.
