BitDecoding: Unlocking Tensor Cores for Long-Context LLMs with Low-Bit KV Cache

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Du, Dayou, Cao, Shijie, Cheng, Jianyi, Mai, Luo, Cao, Ting, Yang, Mao
Format:	Preprint
Published:	2025
Subjects:	Hardware Architecture Artificial Intelligence Computation and Language Performance
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2503.18773