@misc{zhang2024edgeshard, title={EdgeShard: Efficient LLM Inference via Collaborative Edge Computing}, author={Mingjin Zhang and Jiannong Cao and Xiaoming Shen and Zeyang Cui}, year={2024}, eprint={2405.14371}, archivePrefix={arXiv}, primaryClass={cs.DC}, url={https://arxiv.org/abs/2405.14371} }