@article{metronholisticperformanceevaluation, title = {Etalon: Holistic Performance Evaluation Framework for LLM Inference Systems}, author = {Amey Agrawal and Anmol Agarwal and Nitin Kedia and Jayashree Mohan and Souvik Kundu and Nipun Kwatra and Ramachandran Ramjee and Alexey Tumanov}, year = {2024}, eprint = {2407.07000}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2407.07000v2}, }