@article{efficientllmtrainingandservingwith,
  title = {S2-Attention: Hardware-Aware Context Sharding Among Attention Heads},
  author = {Xihui Lin and Yunan Zhang and Suyu Ge and Liliang Ren and Barun Patra and Vishrav Chaudhary and Hao Peng and Xia Song},
  year = {2024},
  eprint = {2407.17678},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.17678v6},
}