ggml/llama.cpp releases: b11055

TL;DR

The ggml/llama.cpp project released version b11055, which includes support for GEGLU_QUICK in hexagon models. This update enhances the model's performance by optimizing certain computations, making it more efficient and potentially improving user experience on compatible devices.

Detailed Summary

The ggml/llama.cpp project released version b11055, which includes support for GEGLU_QUICK in the hexagon branch. This update was made through pull request #29114 and is available on GitHub. The broader impact may include enhanced performance or functionality for users of the llama.cpp library, particularly those working with GEGLU_QUICK.

Key Points

• • Adds support for GEGLU_QUICK in hexagon
• • Released version b11055
• • Available on macOS Apple Silicon (arm64)