@article{minillmmemoryefficientstructuredpruning,
  title = {MINI-LLM: Memory-Efficient Structured Pruning for Large Language Models},
  author = {Hongrong Cheng and Miao Zhang and Javen Qinfeng Shi},
  year = {2024},
  eprint = {2407.11681},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.11681v1},
}