The new generation of rack-built AI server products takes the lead in supporting PCIe 4.0 technology, supports 8 A800s in 4U space, supports industry-leading AI computing power, provides higher performance output, and further improves inter-card communication performance. Continue the high-quality, highly compatible design of the previous generation, achieve better video memory and performance expansion, and significantly accelerate AI model training.

A new generation of rack AI server products, using NVIDIA NVlink interconnection technology, support 8 A800 in a 4U space, support NVLink600GB/s bandwidth interconnection between two adjacent cards, release powerful computing power, and further improve the communication performance between cards. Achieve better video memory and performance scaling to dramatically accelerate AI model training.