Models & Labs
llama.cpp b9243 Release Expands Platform Support
llama.cpp Releaseshigh confidence
Why it matters
- →Expands platform compatibility, making it more accessible to developers on different systems.
- →Enhances support for both AMD and NVIDIA GPUs, reducing hardware limitations.
- →Positions llama.cpp as a versatile tool for diverse GPU architectures.
The b9243 release of llama.cpp has been announced, featuring expanded support across various platforms. This update includes compatibility with macOS Apple Silicon, Ubuntu with ROCm 7.2, and Windows with CUDA 12 and 13, among others. The release does not introduce new models but enhances the runtime environment for different hardware configurations, including Vulkan and SYCL support. This positions llama.cpp as a versatile tool for developers working with diverse GPU architectures, aiming to be a universal inference runtime. The update reflects llama.cpp's ongoing efforts to broaden its platform reach and support.
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 b9063 Release Expands Platform Support
llama.cpp Releases · May 8, 2026 · Same story
What happened next
- 2llama.cpp b9240 Release Expands Platform Support
llama.cpp Releases · May 20, 2026 · Same story
Follow this story
Open the full 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.
