@article{asynctlsefficientgenerativellminferencew,
  title = {AsyncTLS: Efficient Generative LLM Inference with Asynchronous Two-level Sparse Attention},
  author = {Yuxuan Hu and Jianchao Tan and Jiaqi Zhang and Wen Zan and Pingwei Sun and Yifan Lu and Yerui Sun and Yuchen Xie and Xunliang Cai and Jing Zhang},
  year = {2026},
  eprint = {2604.07815},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.07815},
}