@article{tpillmserving70bscalellmsefficientlyon,
  title = {TPI-LLM: Serving 70B-scale LLMs Efficiently on Low-resource Edge Devices},
  author = {Zonghang Li and Wenjiao Feng and Mohsen Guizani and Hongfang Yu},
  year = {2024},
  eprint = {2410.00531},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.00531v1},
}