@article{moeinferencebenchperformanceevaluationof,
  title = {MoE-Inference-Bench: Performance Evaluation of Mixture of Expert Large Language and Vision Models},
  author = {Krishna Teja Chitty-Venkata and Sylvia Howland and Golara Azar and Daria Soboleva and Natalia Vassilieva and Siddhisanket Raskar and Murali Emani and Venkatram Vishwanath},
  year = {2025},
  eprint = {2508.17467},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2508.17467},
}