@article{towardslowbitcommunicationfortensor,
  title = {Towards Low-bit Communication for Tensor Parallel LLM Inference},
  author = {Harry Dong and Tyler Johnson and Minsik Cho and Emad Soroush},
  year = {2024},
  eprint = {2411.07942},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2411.07942v1},
}