llama.cpp update b10930 allows model downloads at server limits.

Core summary

One sentence to understand this update

The llama.cpp project released version b10930, which includes a fix allowing model downloads to respect server-defined limits, as well as supporting macOS/iOS.

Impact & opportunity

What this could mean

This update improves server management and stability for llama.cpp deployments, simplifying model distribution and ensuring resource limits are respected for developers hosting models.