@article{communicationefficientmultidevice,
  title = {Communication-Efficient Multi-Device Inference Acceleration for Transformer Models},
  author = {Xiao Liu and Lijun Zhang and Deepak Ganesan and Hui Guan},
  year = {2025},
  eprint = {2505.19342},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.19342v1},
}