ACE: Adaptive Calibration-Free Expert Skipping for MoE-based LLMs
ACE is proposed, a training-free, calibration-free, and checkpoint-preserving framework for token-adaptive expert skipping in MoE-based LLMs that consistently outperforms existing static and dynamic baselines.
Zu-Kang Xu, Zhi-Xiong Zhao, Xing Hu et al.
· 0 citations