Open Source
llama.cpp b10952 Release Expands Platform Support
llama.cpp Releaseshigh confidence
Why it matters
- →Expands llama.cpp's compatibility with diverse hardware setups.
- →Enhances utility for developers beyond the NVIDIA ecosystem.
- →Strengthens llama.cpp's position as a flexible AI inference tool.
The latest b10952 release of llama.cpp expands its platform support, offering compatibility with various systems such as macOS, Linux, Windows, and openEuler. This update includes Vulkan and ROCm 10.0 support on Ubuntu, and CUDA 12 and 13 on Windows, catering to developers using different hardware setups. Although KleidiAI support on macOS Apple Silicon is disabled, the release enhances llama.cpp's versatility for AI inference. This update focuses on broadening hardware compatibility rather than introducing new models.
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 b10661 Release Expands Platform Support
llama.cpp Releases · August 28, 2026 · Same story
- 2llama.cpp b10797 Release Expands Platform Support
llama.cpp Releases · September 5, 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.
