@article{flashcommunicationreducingtensor,
  title = {Flash Communication: Reducing Tensor Parallelization Bottleneck for Fast Large Language Model Inference},
  author = {Qingyuan Li and Bo Zhang and Liang Ye and Yifan Zhang and Wei Wu and Yerui Sun and Lin Ma and Yuchen Xie},
  year = {2024},
  eprint = {2412.04964},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2412.04964v2},
}