Open Source
llama.cpp b9172 Release Expands Platform Support
llama.cpp Releaseshigh confidence
Why it matters
- →Expands platform compatibility, making AI tools more accessible to developers.
- →Supports a wide range of hardware, enhancing deployment flexibility.
- →Strengthens llama.cpp's position as a versatile AI inference tool.
The b9172 release of llama.cpp has been announced, featuring expanded support for various platforms including macOS, Linux, Windows, and Android. Key additions include ROCm 7.2 support for Ubuntu x64 and Vulkan support across multiple systems. This update enhances the tool's versatility, allowing developers to deploy AI models on a broader range of hardware configurations. While the release doesn't introduce new model architectures, it strengthens llama.cpp's role as a flexible inference runtime.
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 b9190 Release Expands Platform Support
llama.cpp Releases · May 17, 2026 · Same story
- 2llama.cpp b9292 Release Expands Platform Support
llama.cpp Releases · May 23, 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.
