@article{enablingefficientserverlessinference,
  title = {Enabling Efficient Serverless Inference Serving for LLM (Large Language Model) in the Cloud},
  author = {Himel Ghosh},
  year = {2024},
  eprint = {2411.15664},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2411.15664v1},
}