llama.cpp b10075 Update: Four Improvements to the Local AI Engine

The llama.cpp b10075 update introduces four key improvements to the local AI inference engine. These enhancements focus on performance, memory efficiency, and new features for running large language models locally.

Meta

Zhipu builds data center using only domestic chips

Zhipu has announced the construction of a data center powered entirely by domestically produced chips. The move is part of China's push for self-sufficiency in AI infrastructure.