@article{flashmlaetapefficienttransposeattention,
  title = {FlashMLA-ETAP: Efficient Transpose Attention Pipeline for Accelerating MLA Inference on NVIDIA H20 GPUs},
  author = {Pengcuo Dege and Qiuming Luo and Rui Mao and Chang Kong},
  year = {2025},
  eprint = {2506.01969},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2506.01969v2},
}