@article{largelanguagemodelpartitioningforlow,
  title = {Large Language Model Partitioning for Low-Latency Inference at the Edge},
  author = {Dimitrios Kafetzis and Ramin Khalili and Iordanis Koutsopoulos},
  year = {2025},
  eprint = {2505.02533},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.02533v1},
}