@article{llmbipstructuredpruningforlargelanguage,
  title = {LLM-BIP: Structured Pruning for Large Language Models with Block-Wise Forward Importance Propagation},
  author = {Haihang Wu},
  year = {2024},
  eprint = {2412.06419},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2412.06419v1},
}