@article{efficientedgellmsdeploymentviahessianawa,
  title = {Efficient Edge LLMs Deployment via HessianAware Quantization and CPU GPU Collaborative},
  author = {Tuo Zhang and Ning Li and Xin Yuan and Wenchao Xu and Quan Chen and Song Guo and Haijun Zhang},
  year = {2025},
  eprint = {2508.07329},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2508.07329},
}