T-Head releases Zhenwu V900 training-and-inference integrated AI chip

T-Head releases the new-generation Zhenwu V900 training-and-inference integrated AI chip. According to Jiwei.com, the chip was released on September 22 at the Hangzhou Yunqi Conference; single-chip performance reaches three times that of Zhenwu M890, can meet the training and inference needs of trillion-parameter large models, and is planned for mass production and sale in the first quarter of 2027. The report says Zhenwu V900 carries 216GB of memory, chip-to-chip interconnect bandwidth of 1200GB/s, natively supports FP8 and FP4 low-precision computing, and can form a thousand-card full-bandwidth high-speed interconnect super node with the self-developed ICN Switch interconnect chip. T-Head also for the first time announced its Yitian server CPU plan, with Yitian 720 and Yitian 730 to be launched in 2027. There are currently no subsequent development facts.

AI-generated from public reports

1. Report date Oct 22· 1 reports

   Pingtouge releases Zhenwu V900, an integrated training-and-inference AI chip

   Source:Jiwei.com