@misc{zhang2024edge,
  title={Edge Intelligence Optimization for Large Language Model Inference with Batching and Quantization},
  author={Xinyuan Zhang and Jiang Liu and Zehui Xiong and Yudong Huang and Gaochang Xie and Ran Zhang},
  year={2024},
  eprint={2405.07140},
  archivePrefix={arXiv},
  primaryClass={cs.LG},
  url={https://arxiv.org/abs/2405.07140}
}