@article{notallexpertsareequalefficientexpert, title = {Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models}, author = {Xudong Lu and Qi Liu and Yuhui Xu and Aojun Zhou and Siyuan Huang and Bo Zhang and Junchi Yan and Hongsheng Li}, year = {2024}, eprint = {2402.14800}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2402.14800v2}, }