Huawei unveils Atlas 950 SuperCluster — promises 1 ZettaFLOPS FP4 performance and features hundreds of thousands of 950DT APUs

Huawei has introduced the Atlas 950 SuperCluster, a high-performance AI solution featuring 1 ZettaFLOPS FP4 performance and hundreds of thousands of Ascend 950DT NPUs. The system is designed to compete with Nvidia's Rubin-based systems by late 2026. The SuperCluster comprises 64 Atlas 950 SuperPoDs with 524,288 AI accelerators spread across over 10,240 interconnected cabinets, offering up to 524 FP8 ExaFLOPS for AI training and 1 FP4 ZettaFLOPS for AI inference. Huawei positions the SuperCluster to support large-scale AI models with billions to trillions of parameters, emphasizing compute throughput, interconnect bandwidth, and system stability. Huawei also revealed plans for the Atlas 960 SuperCluster in late 2027, promising even higher performance with over 1 million Ascend 960 NPUs.