@inproceedings{
cho2026optimizing,
title={Optimizing Deployment Configurations for {LLM} Inference},
author={Sung Min Cho and Jaewon Lee and Chunqiang Tang and Yejin Lee and Geonhwa Jeong and Anca Agape and Scott Batura and Vincent Boivin and Stephen Chen and Renfei Chen and Sijia Chen and Yan Cui and Bradley Davis and Zhaoxia (Summer) Deng and Nick Egebo and Emad El-Haraty and Sebastien Estienne and Lu Fang and Lu Fang and Josh Fromm and Raj Ganapathy and Vedanuj Goswami and Leo Guo and Ye Hu and Chenheli Hua and Jianyu Huang and Aya Ibrahim and Niranjan Jagannath and Hongyi Jia and Changkyu Kim and Shikai Li and Brandon Liu and Jiawen Liu and Ajit Mathews and Xiaozhu Meng and Vlad Tiberiu Mihailescu and Amit Nagpal and Maxim Naumov and Michal Ostrowski and Jialin Ouyang and Jason Park and Sarunya Pumma and Ye Qi and Zixi Qi and Jeremy Reizenstein and Rajasi Saha and Nandhini Santhanam and Zhan Shu and Ruan Silva and Grigory Sizov and Jon Maltiel Swenson and Brandon Taylor and Chris Thi and Adolfo Victoria and Yunfan Wang and Pengchao Wang and Wenchen Wang and Xiaodong Wang and Bram Wasti and Wei Xu and Qirui Yang and Jingyi Yang and Hector Yuen and Zhengyuan Zhang and Jing Zhang and Jenny Zhen and Yanjun Zhou},
booktitle={Ninth Conference on Machine Learning and Systems},
year={2026},
url={https://openreview.net/forum?id=gEbKQeIdxB}
}