@article{packinfercomputeandioefficientattentionf,
  title = {PackInfer: Compute- and I/O-Efficient Attention for Batched LLM Inference},
  author = {Rui Ning and Wei Zhang and Fan Lai},
  year = {2026},
  eprint = {2602.06072},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.06072},
}