@article{cqilinferencelatencyoptimizationwith,
  title = {CQIL: Inference Latency Optimization with Concurrent Computation of Quasi-Independent Layers},
  author = {Longwei Zou and Qingyang Wang and Han Zhao and Jiangang Kong and Yi Yang and Yangdong Deng},
  year = {2024},
  eprint = {2404.06709},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2404.06709v2},
}