TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tang, Xiaojuan, Meng, Fanxu, Tang, Pingzhi, Wang, Yuxuan, Yin, Di, Sun, Xing, Zhang, Muhan
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2508.15881