<ul><li>A team associated with China’s Tsinghua University has released a new open source AI framework named Chitu.</li><li>Chitu is a high-performance inference framework for large language models, challenging the dominance of NVIDIA's GPUs.</li><li>It supports various mainstream language models and aims to provide versatility in deploying requirements.</li><li>The framework claims to achieve a 315% increase in model inference speed while reducing GPU usage by 50% compared to foreign open source frameworks.</li></ul>

A New Chinese Open Source Framework Aims to Challenge Dependence on NVIDIA’s Chips on AI Models

Discover more