%0 Journal Article %1 journals/corr/abs-2404-08509 %A Qiu, Haoran %A Mao, Weichao %A Patke, Archit %A Cui, Shengkun %A Jha, Saurabh %A Wang, Chen %A Franke, Hubertus %A Kalbarczyk, Zbigniew T. %A Basar, Tamer %A Iyer, Ravishankar K. %D 2024 %J CoRR %K dblp %T Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction. %U http://dblp.uni-trier.de/db/journals/corr/corr2404.html#abs-2404-08509 %V abs/2404.08509

@article{journals/corr/abs-2404-08509, added-at = {2024-05-16T00:00:00.000+0200}, author = {Qiu, Haoran and Mao, Weichao and Patke, Archit and Cui, Shengkun and Jha, Saurabh and Wang, Chen and Franke, Hubertus and Kalbarczyk, Zbigniew T. and Basar, Tamer and Iyer, Ravishankar K.}, biburl = {https://www.bibsonomy.org/bibtex/21d2c9e089ce67bf77193c2bf9039adac/dblp}, ee = {https://doi.org/10.48550/arXiv.2404.08509}, interhash = {fcdb2d0770d9ffca2f2f7de6a2307b27}, intrahash = {1d2c9e089ce67bf77193c2bf9039adac}, journal = {CoRR}, keywords = {dblp}, timestamp = {2024-05-20T07:10:26.000+0200}, title = {Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction.}, url = {http://dblp.uni-trier.de/db/journals/corr/corr2404.html#abs-2404-08509}, volume = {abs/2404.08509}, year = 2024 }