Models & Labs
llama.cpp b10569 release enhances compatibility
llama.cpp Releaseshigh confidence
Why it matters
- →Enhances compatibility across multiple platforms, broadening developer access.
- →Improves performance with technical updates like dots3-note.
- →Supports CUDA 12 and 13, enhancing GPU compatibility on Windows.
The b10569 release of llama.cpp brings a series of technical updates aimed at improving performance and compatibility. Key changes include the addition of dots3-note and enhancements to the llama_kv_cache_dsa_iswa. The update supports a wide range of platforms, including macOS, Linux, and Windows, with specific enhancements for CUDA 12 and 13 on Windows. This release continues to build on llama.cpp's versatility, making it a more robust tool for developers across various 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 releases version 0.3.0
llama.cpp Releases · August 26, 2026 · Same story
- 2llama.cpp b10989 Release Expands Platform Support
llama.cpp Releases · September 16, 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.
