TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference

@misc{meng2025tplatensorparallel,
      title={TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill \& Decode Inference},
      author={Fanxu Meng and Muhan Zhang and Yuxuan Wang and Di Yin and Xing Sun and Xiaojuan Tang and Pingzhi Tang},
      year={2025},
      eprint={2508.15881},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2508.15881},
}