@article{exploitingsparsityforlongcontext,
  title = {Exploiting Sparsity for Long Context Inference: Million Token Contexts on Commodity GPUs},
  author = {Ryan Synk and Monte Hoover and John Kirchenbauer and Neel Jain and Alex Stein and Manli Shu and Josue Melendez Sanchez and Ramani Duraiswami and Tom Goldstein},
  year = {2025},
  eprint = {2502.06766},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.06766v2},
}