@article{echolmacceleratingllmservingwithreal, title = {EchoLM: Accelerating LLM Serving with Real-time Knowledge Distillation}, author = {Yifan Yu and Yu Gan and Lillian Tsai and Nikhil Sarda and Jiaming Shen and Yanqi Zhou and Arvind Krishnamurthy and Fan Lai and Henry M. Levy and David Culler}, year = {2025}, eprint = {2501.12689}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2501.12689v2}, }