Skip to content

From Buffers to Registers: Unlocking Fine-Grained FlashAttention with Hybrid-Bonded 3D NPU Co-Design.

Jinxin Yu, Yudong Pan, Mengdi Wang, Huawei Li, Yinhe Han, Xiaowei Li, Ying Wang

VenueADATE
Year2026
ProceedingsDATE

Browse the full DATE paper archive.