@article{lserveefficientlongsequencellmserving,
  title = {LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention},
  author = {Shang Yang and Junxian Guo and Haotian Tang and Qinghao Hu and Guangxuan Xiao and Jiaming Tang and Yujun Lin and Zhijian Liu and Yao Lu and Song Han},
  year = {2025},
  eprint = {2502.14866},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.14866v2},
}