@article{emoetaskawarememoryefficientmixtureof,
  title = {eMoE: Task-aware Memory Efficient Mixture-of-Experts-Based (MoE) Model Inference},
  author = {Suraiya Tairin and Shohaib Mahmud and Haiying Shen and Anand Iyer},
  year = {2025},
  eprint = {2503.06823},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2503.06823v1},
}