llama.cpp Release b9490: ggml-cpu SVE Width and Platform Updates

Core summary

One sentence to understand this update

llama.cpp's b9490 release includes a new ggml-cpu feature to use runtime SVE width in FWHT and provides updated builds for various platforms including macOS, iOS, and Linux.

Impact & opportunity

What this could mean

Builders working with llama.cpp can expect improved CPU performance with SVE optimizations and broader platform support for their local LLM deployments.