BibTeX record journals/corr/abs-2403-02310

• > Home > journals/corr/abs-2403-02310

@article{DBLP:journals/corr/abs-2403-02310,
  author       = {Amey Agrawal and
                  Nitin Kedia and
                  Ashish Panwar and
                  Jayashree Mohan and
                  Nipun Kwatra and
                  Bhargav S. Gulavani and
                  Alexey Tumanov and
                  Ramachandran Ramjee},
  title        = {Taming Throughput-Latency Tradeoff in {LLM} Inference with Sarathi-Serve},
  journal      = {CoRR},
  volume       = {abs/2403.02310},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2403.02310},
  doi          = {10.48550/ARXIV.2403.02310},
  eprinttype    = {arXiv},
  eprint       = {2403.02310},
  timestamp    = {Tue, 02 Apr 2024 16:35:34 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2403-02310.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}