Product
PPU 810
A domestic AI accelerator card from Baidu's Kunlunxin, featuring 96GB of memory per card and targeting large model inference and training scenarios.
Timeline (last 90 days)
Oct 14
AntAngelMed's BF16 full-precision inference requires 8 Ascend 910B (64GB) cards or 4 Kunlun P800/PPU 810 (96GB) cards.
Unverified50%