@article{cmoefastcarvingofmixtureofexpertsfor, title = {CMoE: Fast Carving of Mixture-of-Experts for Efficient LLM Inference}, author = {Zehua Pei and Lancheng Zou and Hui-Ling Zhen and Xianzhi Yu and Wulong Liu and Sinno Jialin Pan and Mingxuan Yuan and Bei Yu}, year = {2025}, eprint = {2502.04416}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2502.04416v1}, }