Alibaba Launches 128-GPU Supernode Server With Zhenyu M890 Chip for Agent Inference on May 20

Alibaba unveiled a 128-GPU supernode server powered by the Zhenyu M890 AI chip from subsidiary Pingtousheng on May 20 at the Alibaba Cloud Summit. The server integrates the ICN Switch 1.0 interconnect chip, achieving sub-100-nanosecond communication latency and enabling 128 AI chips to function as a single computer. The system is designed to support concurrent inference and large language model training for the Agentic era.
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