@article{besapruninglargelanguagemodelswith,
  title = {BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation},
  author = {Peng Xu and Wenqi Shao and Mengzhao Chen and Shitao Tang and Kaipeng Zhang and Peng Gao and Fengwei An and Yu Qiao and Ping Luo},
  year = {2024},
  eprint = {2402.16880},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.16880v2},
}