Huawei Launches Xinghe AI Fabric 2.0, Empowering Enterprises to Create Always-on Data Center Networks with Full Computing Power

During Huawei Connect 2025, the inaugural Data Center Innovation Summit, themed “Leading AI DC Innovation for an Intelligent Future”, was successfully held.Huawei joined over 600 industry leaders, experts, and scholars from around the world to engage in in depth discussions on high quality construction and sustainable development of data center infrastructure in the AI era. At the summit, Huawei officially unveiled its Xinghe AI Fabric 2.0 solution – a comprehensive upgrade to the AI Fabric first launched in 2018 – empowering enterprises to create always on data center networks with full computing power and injecting fresh momentum into their digital-intelligent transformation.

In his keynote, Arthur Wang noted that the rapid iteration of AI technologies and the continuous evolution of cloud based architectures are driving data center networks to a critical inflection point. In response, Huawei has launched the AI era ready Xinghe AI Fabric 2.0 solution, built on a three layer architecture comprising AI Brain, AI Connectivity, and AI Network Elements. The solution integrates the AI network agent (NetMaster), StarryWing Digital Map (three level automation), Xinghuan training + Xingzhi inference scheduling engine, and Rock Solid Architecture, creating always on data center networks with full computing power.

Xinghe AI Fabric 2.0 – Creating Always on Data Center Networks with Full Computing Power

• AI Brain: Powered by Huawei’s exclusive StarryWing Digital Map and NetMaster, the solution enables drag and drop service orchestration and automated deployment, integrated application network O&M automation, and end to end automation across heterogeneous networks and security domains – significantly boosting O&M efficiency.
• AI Connectivity: Utilizes the network scale load balancing (NSLB) algorithm series to increase network throughput to 95% and improve training/inference efficiency by over 10%. With the iReliable three layer reliability technology built on the Rock Solid Architecture, overall reliability is enhanced tenfold.
• AI Network Elements: By leveraging the CloudEngine series general purpose computing switches, the XH series intelligent computing switches, and StarryLink optical modules, the solution delivers high precision traffic awareness and visualization of packet loss and latency; the intrinsic security technologies and group-based isolation capabilities help comprehensively strengthen network security.

Show Floor Highlights – Demonstrating Core Technical Strengths
At the event, the Huawei Data Center Network booth showcased the Xinghe AI Fabric 2.0 solution through dynamic demonstrations and real world simulations, vividly illustrating the advantages of its three layer architecture – AI Brain, AI Connectivity, and AI Network Elements – and allowing visitors to clearly experience the real world value of “AI for Fabric & Fabric for AI.”

Also on display were Huawei’s full portfolio of 800GE products – including the industry’s highest density 128×800GE fixed switch XH9330, the 64×800GE fixed switch XH9320, and the complete range of 800GE StarryLink optical modules – along with the Xinghe liquid cooled cabinet and the industry’s first all port liquid cooled high density 128×400GE fixed switch XH9230 LC.

Looking ahead, Huawei will continue to uphold its philosophy of open collaboration, working hand in hand with partners and customers to drive ongoing innovation. Also, it will deepen research and innovation in data center networking, advance intelligent network upgrades and generational evolution, and create greater value for industries and customers alike.