@article{sarathiefficientllminferenceby,
  title = {SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills},
  author = {Amey Agrawal and Ashish Panwar and Jayashree Mohan and Nipun Kwatra and Bhargav S. Gulavani and Ramachandran Ramjee},
  year = {2023},
  eprint = {2308.16369},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2308.16369v1},
}