llama.cpp Releases b9789 with MoE Quantization Fix and Platform Support

Core summary

One sentence to understand this update

llama.cpp released version b9789, which includes a fix for quantizing Mixture-of-Experts (MoE) models and outlines supported platforms.

Impact & opportunity

What this could mean

This update improves the efficiency and compatibility of running quantized MoE models on various hardware, especially for local LLM deployment.