@article{leanattentionhardwareawarescalable,
  title = {Lean Attention: Hardware-Aware Scalable Attention Mechanism for the Decode-Phase of Transformers},
  author = {Rya Sanovar and Srikant Bharadwaj and Renee St. Amant and Victor Rühle and Saravan Rajmohan},
  year = {2024},
  eprint = {2405.10480},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2405.10480v2},
}