HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference
Ping Gong, Jiawei Yi, Shengnan Wang, Juncheng Zhang, Zewen Jin, Ouxiang Zhou, Ruibo Liu, Guanbin Xu, Youhui Bai, Bowen Ye, Kun Yuan, Tong Yang, Gong Zhang, Renhai Chen, Feng Wu, Cheng Li. Findings of the Association for Computational Linguistics: ACL 2025. 2025.
Authors
- Youhui Bai
- Kun Yuan (ORCID: https://orcid.org/0009-0003-9425-7842)
- Renhai Chen (ORCID: https://orcid.org/0000-0002-0233-5838)
- Juncheng Zhang (ORCID: https://orcid.org/0000-0002-1479-1793)
- Ouxiang Zhou
- Jiawei Yi (ORCID: https://orcid.org/0000-0003-0325-7146)
- Guanbin Xu
- Shengnan Wang (ORCID: https://orcid.org/0000-0002-3923-4571)
- Gong Zhang (ORCID: https://orcid.org/0000-0003-0283-7050)
- Li Cheng (ORCID: https://orcid.org/0000-0002-5168-7768)
- Feng Wu (ORCID: https://orcid.org/0000-0003-0832-5486)
- Yang Tong (ORCID: https://orcid.org/0009-0001-1134-2204)
- Bin Ye (ORCID: https://orcid.org/0000-0003-4174-9133)
- Zewen Jin (ORCID: https://orcid.org/0000-0002-4762-6559)
- Ping Gong
- R.P. Liu
Publication Details
- Published
- 2025-01-01
- DOI
- https://doi.org/10.18653/v1/2025.findings-acl.1275
- Primary Topic
- Advanced Neural Network Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Chinese Academy of Sciences