@article{h1bkvhybridonebitcachesformemoryefficien,
  title = {H1B-KV: Hybrid One-Bit Caches for Memory-Efficient Large Language Model Inference},
  author = {Harshil Vejendla},
  year = {2025},
  eprint = {2510.05529},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2510.05529},
}