Cite
Notes
Only stored in your browser.
Attribution
HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference
arXiv 2025
from 1 papers
Bowen Ye
Cheng Li
Feng Wu
Gong Zhang
Guanbin Xu
Jiawei Yi
Juncheng Zhang
Kun Yuan
Ouxiang Zhou
Ping Gong