BatchLLM: Optimizing Large Batched LLM Inference with Global Prefix Sharing and Throughput-oriented Token Batching

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zheng, Zhen, Ji, Xin, Fang, Taosong, Zhou, Fanghao, Liu, Chuanjie, Peng, Gang
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Artificial Intelligence Distributed, Parallel, and Cluster Computing Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2412.03594