Models & Labs
llama.cpp b9590 Release Fixes JSON Schema Handling
llama.cpp Releaseshigh confidence
Why it matters
- →Fixing the json_schema handling improves data integrity for developers.
- →The update supports a wide range of platforms, increasing accessibility.
- →It addresses a critical issue, enhancing the tool's reliability.
The b9590 release of llama.cpp fixes an issue with the LFM2 template handler that was ignoring json_schema from response_format, only building a grammar for tool-calling. This update is significant for developers who need accurate JSON schema handling. The release includes builds for various platforms, including macOS, Linux, Windows, and openEuler, although some features remain disabled. This update enhances the tool's reliability for handling complex data formats.
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 b10936 Release Enhances Parsing
llama.cpp Releases · September 13, 2026 · Same story
- 2Llama.cpp b10934 Release Enhances JSON Schema Handling
llama.cpp Releases · September 13, 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.
