Meituan Releases LongCat-2.0 Trillion-Parameter Model with 30T Tokens on June 30

According to Jin10, Meituan released LongCat-2.0, a new trillion-parameter large language model, on June 30 and announced its open-source availability. The model's pretraining dataset exceeds 30 trillion tokens and covers Chinese, English, multiple languages, and code. Meituan's team addressed hardware and computational challenges in large-scale training across ten thousand GPUs, improving system stability and reducing monthly average daily failure rate by over 70 percent through automated recovery mechanisms and consistency verification protocols.
Disclaimer: The information on this page may come from third-party sources and is for reference only. It does not represent the views or opinions of Gate and does not constitute any financial, investment, or legal advice. Virtual asset trading involves high risk. Please do not rely solely on the information on this page when making decisions. For details, see the Disclaimer.
Comment
0/400
No comments