Jet-RL: Enabling On-Policy FP8 Reinforcement Learning with Unified Training and Rollout Precision Flow

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xi, Haocheng, Ruan, Charlie, Liao, Peiyuan, Lin, Yujun, Cai, Han, Zhao, Yilong, Yang, Shuo, Keutzer, Kurt, Han, Song, Zhu, Ligeng
Format:	Preprint
Published:	2026
Subjects:	Machine Learning 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/2601.14243