@misc{wang2024model,
  title={Model Compression and Efficient Inference for Large Language Models: A Survey},
  author={Wenxiao Wang and Wei Chen and Yicong Luo and Yongliu Long and Zhengkai Lin and Liye Zhang and Binbin Lin and Deng Cai and Xiaofei He},
  year={2024},
  eprint={2402.09748},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2402.09748}
}