@article{treeattentiontopologyawaredecodingfor,
  title = {Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters},
  author = {Vasudev Shyam and Jonathan Pilault and Emily Shepperd and Quentin Anthony and Beren Millidge},
  year = {2024},
  eprint = {2408.04093},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2408.04093v3},
}