StagFormer: Time Staggering Transformer Decoding for RunningLayers In Parallel

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cutler, Dylan, Kandoor, Arun, Dikkala, Nishanth, Saunshi, Nikunj, Wang, Xin, Panigrahy, Rina
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!