FlattenQuant: Breaking Through the Inference Compute-bound for Large Language Models with Per-tensor Quantization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Yi, Yang, Fei, Peng, Shuang, Wang, Fangyu, Pan, Aimin
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2402.17985