Models & Labs
llama.cpp releases version 0.3.0
llama.cpp Releaseshigh confidence
Why it matters
- →Expands platform support, making llama.cpp more versatile for developers.
- →Enhances compatibility with new architectures like Apple Silicon and Vulkan.
- →Strengthens llama.cpp's position as a tool for diverse computing environments.
llama.cpp has released version 0.3.0, bringing updates to its platform support and functionality. This version includes enhancements for macOS, Linux, Windows, and openEuler, with notable support for CUDA 13 on Windows and ROCm 7.14 on Ubuntu. The update aims to improve compatibility across various architectures, including Apple Silicon and Vulkan. While no new features are introduced, the release strengthens llama.cpp's utility for developers working in diverse computing environments.
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 Releases New Version with Multi-Platform Support
llama.cpp Releases · April 30, 2026 · Same story
What happened next
- 2llama.cpp b10937 release expands platform support
llama.cpp Releases · September 13, 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.
