@article{hermesmemoryefficientpipelineinference,
  title = {Hermes: Memory-Efficient Pipeline Inference for Large Models on Edge Devices},
  author = {Xueyuan Han and Zinuo Cai and Yichu Zhang and Chongxin Fan and Junhan Liu and Ruhui Ma and Rajkumar Buyya},
  year = {2024},
  eprint = {2409.04249},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2409.04249v2},
}