Models & Labs
llama.cpp b9561 Release Expands Platform Support
llama.cpp Releaseshigh confidence
Why it matters
- →Expands platform compatibility, making llama.cpp more versatile for developers.
- →Enhances support for AMD GPUs with ROCm 7.2, reducing reliance on NVIDIA.
- →Continues to position llama.cpp as a key player in AI inference across diverse systems.
The b9561 release of llama.cpp has been announced, featuring expanded support for various platforms. Notable additions include Vulkan support for both Ubuntu and Windows, as well as ROCm 7.2 for Ubuntu, enhancing compatibility for AMD GPU users. While some features like KleidiAI on macOS and SYCL on Windows are disabled, the update continues to position llama.cpp as a versatile tool for AI inference across multiple systems. This release does not introduce new models but focuses on improving the existing infrastructure.
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.
How we got here
- 1llama.cpp b9571 Release Expands Platform Support
llama.cpp Releases · June 9, 2026 · Same story
What happened next
- 2llama.cpp b10599 Release Expands Platform Support
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.
