Models & Labs
llama.cpp b9655 Release Fixes Grammar Bug
llama.cpp Releaseshigh confidence
Why it matters
- →Fixing the grammar generator bug improves language processing reliability.
- →The update enhances the accuracy of the PEG parser test.
- →Developers benefit from a more stable and dependable tool across platforms.
The b9655 release of llama.cpp focuses on fixing a persistent grammar generator bug that reappeared in recent changes. This update is critical for developers who depend on accurate grammar parsing in their applications. Additionally, the release updates an erroneous case in the PEG parser test, further refining the tool's parsing accuracy. Although no new features are introduced, the release strengthens the existing framework, providing a more stable environment for developers across multiple operating systems.
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 b9754 Release Enhances Grammar Parsing
llama.cpp Releases · June 22, 2026 · Same story
- 2llama.cpp b10618 Release Enhances Parsing
llama.cpp Releases · August 26, 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.
