StreamRL: Scalable, Heterogeneous, and Elastic RL for LLMs with Disaggregated Stream Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhong, Yinmin, Zhang, Zili, Song, Xiaoniu, Hu, Hanpeng, Jin, Chao, Wu, Bingyang, Chen, Nuo, Chen, Yukun, Zhou, Yu, Wan, Changyi, Zhou, Hongyu, Jiang, Yimin, Zhu, Yibo, Jiang, Daxin
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Distributed, Parallel, and Cluster Computing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2504.15930