XQuant: Breaking the Memory Wall for LLM Inference with KV Cache Rematerialization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tomar, Aditya, Hooper, Coleman, Lee, Minjae, Xi, Haocheng, Tiwari, Rishabh, Kang, Wonjun, Manolache, Luca, Mahoney, Michael W., Keutzer, Kurt, Gholami, Amir
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2508.10395