SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Jonathan, Farahini, Nasim, Iuliugin, Evgenii, Vesterlund, Magnus, Häggström, Christian, Wang, Guangtao, Upasani, Shubhangi, Sachdeva, Ayush, Li, Rui, Fu, Faline, Wu, Chen, Siddiqua, Ayesha, Long, John, Zhao, Tuowen, Musaddiq, Matheen, Zeffer, Håkan, Du, Yun, Wang, Mingran, Li, Qinghua, Li, Bo, Thakker, Urmish, Prabhakar, Raghu
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Hardware Architecture Distributed, Parallel, and Cluster Computing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2511.03092