Open Source
llama.cpp b9063 Release Expands Platform Support
llama.cpp Releaseshigh confidence
Why it matters
- →Expands platform support, making llama.cpp more versatile for developers.
- →Enhances compatibility with both AMD and NVIDIA hardware, broadening its user base.
- →Focuses on runtime improvements, ensuring better performance across diverse systems.
The b9063 release of llama.cpp has been announced, featuring expanded support across multiple platforms. This update includes compatibility with macOS Apple Silicon, Ubuntu with ROCm 7.2, and Windows with CUDA 13.1, among others. The release does not introduce new models but enhances the runtime environment for various hardware configurations, including Vulkan and SYCL support. This positions llama.cpp as a versatile tool for developers working with different GPU and CPU architectures, reinforcing its role as a comprehensive inference runtime solution.
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 b9097 Release Expands Platform Support
llama.cpp Releases · May 11, 2026 · Same story
- 2llama.cpp b9243 Release Expands Platform Support
llama.cpp Releases · May 20, 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.
