llama.cpp Release b9439: iGPU usage and platform support

Core summary

One sentence to understand this update

The llama.cpp project released version b9439, which defaults to using only one iGPU device and continues to support various platforms like macOS Apple Silicon, iOS, and Linux.

Impact & opportunity

What this could mean

Developers can benefit from optimized iGPU utilization for running local LLMs and expanded platform compatibility, enhancing local AI deployment.