@article{lazyllmdynamictokenpruningforefficient,
  title = {LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference},
  author = {Qichen Fu and Minsik Cho and Thomas Merth and Sachin Mehta and Mohammad Rastegari and Mahyar Najibi},
  year = {2024},
  eprint = {2407.14057},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.14057v1},
}