@misc{abhyankar2024apiserve, title={APIServe: Efficient API Support for Large-Language Model Inferencing}, author={Reyna Abhyankar and Zijian He and Vikranth Srivatsa and Hao Zhang and Yiying Zhang}, year={2024}, eprint={2402.01869}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2402.01869} }