@article{communicationcompressionfortensorparalle,
  title = {Communication Compression for Tensor Parallel LLM Inference},
  author = {Jan Hansen-Palmus and Michael Truong Le and Oliver Hausdörfer and Alok Verma},
  year = {2024},
  eprint = {2411.09510},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2411.09510v2},
}