SpecEE: Accelerating Large Language Model Inference with Speculative Early Exiting

Open Webpage

Jiaming Xu, Jiayi Pan, Yongkang Zhou, Siming Chen, Jinhao Li, Yaoxiu Lian, Junyi Wu, Guohao Dai

Published: 21 Jun 2025, Last Modified: 12 Mar 2026CrossrefEveryoneRevisionsCC BY-SA 4.0