llama.cpp Release b9439 Optimizes iGPU Use and Updates Platform Support

Core summary

One sentence to understand this update

llama.cpp release b9439 defaults to using only one iGPU device and details continued support for macOS Apple Silicon, iOS, and various Linux environments.

Impact & opportunity

What this could mean

Builders working with local LLMs can expect improved resource management on iGPUs and consistent cross-platform compatibility for llama.cpp.