@article{serverlessllmlocalityenhancedserverless,
  title = {ServerlessLLM: Low-Latency Serverless Inference for Large Language Models},
  author = {Yao Fu and Leyang Xue and Yeqi Huang and Andrei-Octavian Brabete and Dmitrii Ustiugov and Yuvraj Patel and Luo Mai},
  year = {2024},
  eprint = {2401.14351},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2401.14351v2},
}