Home
Alibaba Launches Zhenwu M890128 Card Ultra-Node Server with Hundred-Nanosecond Latency for Agentic Era

At the 2026 Alibaba Cloud Summit, Alibaba unveiled a 128-card ultra-node server powered by Tengyun's next-generation AI chip, the Zhenwu M890. The server integrates Tengyun's proprietary ICN Switch 1.0 interconnect chip, delivering nanosecond-level ultra-low communication latency between chips.
By leveraging an innovative ultra-node architecture, the system seamlessly unifies 128 AI chips into a highly efficient collaborative supercomputer. Designed to tackle the extreme computational demands of the Agentic era, this ultra-node server will focus on handling massive concurrent Agent inference and large-scale model training in core business scenarios.
Related article
Stripe to Acquire OpenRouter as AI Model Routing Gains Momentum
Stripe has agreed to acquire OpenRouter, an AI model-routing platform that gives developers access to hundreds of models through a single interface. The deal adds model selection and routing to Stripe’s existing work around AI usage and token-based b
Former OpenAI Researcher Barrett Zoph Returns to Google to Support Gemini Development
Barret Zoph, who previously abruptly left and joined OpenAI due to a disagreement with Thinking Machines Lab CEO Miriam Mularati, has once again changed employers. Alphabet's Google announced that Zoph will return as Vice President of Research, bring
How Recursive Intelligence Raised $335M at $4B Valuation in 4 Months
The co-founders of startup Ricursive Intelligence seemed destined to be co-founders.Anna Goldie, CEO, and Azalia Mirhoseini, CTO, are so well-known in the AI community that they were among those AI engineers who “got those weird emails from Zuckerber
Related Special Topic Recommendations
Comments (1)
0/500

At the 2026 Alibaba Cloud Summit, Alibaba unveiled a 128-card ultra-node server powered by Tengyun's next-generation AI chip, the Zhenwu M890. The server integrates Tengyun's proprietary ICN Switch 1.0 interconnect chip, delivering nanosecond-level ultra-low communication latency between chips.
By leveraging an innovative ultra-node architecture, the system seamlessly unifies 128 AI chips into a highly efficient collaborative supercomputer. Designed to tackle the extreme computational demands of the Agentic era, this ultra-node server will focus on handling massive concurrent Agent inference and large-scale model training in core business scenarios.
Stripe to Acquire OpenRouter as AI Model Routing Gains Momentum
Stripe has agreed to acquire OpenRouter, an AI model-routing platform that gives developers access to hundreds of models through a single interface. The deal adds model selection and routing to Stripe’s existing work around AI usage and token-based b
Former OpenAI Researcher Barrett Zoph Returns to Google to Support Gemini Development
Barret Zoph, who previously abruptly left and joined OpenAI due to a disagreement with Thinking Machines Lab CEO Miriam Mularati, has once again changed employers. Alphabet's Google announced that Zoph will return as Vice President of Research, bring
How Recursive Intelligence Raised $335M at $4B Valuation in 4 Months
The co-founders of startup Ricursive Intelligence seemed destined to be co-founders.Anna Goldie, CEO, and Azalia Mirhoseini, CTO, are so well-known in the AI community that they were among those AI engineers who “got those weird emails from Zuckerber











