@article{tplatensorparallellatentattentionforeffi,
  title = {TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference},
  author = {Xiaojuan Tang and Fanxu Meng and Pingzhi Tang and Yuxuan Wang and Di Yin and Xing Sun and Muhan Zhang},
  year = {2025},
  eprint = {2508.15881},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2508.15881},
}