@article{rtprethinkingtensorparallelismwithmemory,
  title = {RTP: Rethinking Tensor Parallelism with Memory Deduplication},
  author = {Cheng Luo and Tianle Zhong and Geoffrey Fox},
  year = {2023},
  eprint = {2311.01635},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2311.01635v1},
}