Huawei's SuperNode doubles Nvidia's AI throughput—built to train GPT-5-class models

DIGITIMES • June 30, 2025

At the Ascend AI Developer Summit on May 26, 2025, Huawei unveiled its new Ascend SuperNode architecture, the foundation of its CloudMatrix 384 high-performance AI compute cluster. Comprised of 384 Ascend 910C processors housed across 12 compute cabinets and …

Save my User ID and Password Some subscribers prefer to save their log-in information so they do not have to enter their User ID and Password each time they visit the site. To activate this function… [+307 chars]

Visiting original passage: Huawei's SuperNode doubles Nvidia's AI throughput—built to train GPT-5-class models

Twitter
Facebook
Pinterest
Linkedin

Huawei's SuperNode doubles Nvidia's AI throughput—built to train GPT-5-class models

Modal Title