@inproceedings {280922, author = {Gyeong-In Yu and Joo Seong Jeong and Geon-Woo Kim and Soojeong Kim and Byung-Gon Chun}, title = {Orca: A Distributed Serving System for {Transformer-Based} Generative Models}, booktitle = {16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)}, year = {2022}, isbn = {978-1-939133-28-1}, address = {Carlsbad, CA}, pages = {521--538}, url = {https://www.usenix.org/conference/osdi22/presentation/yu}, publisher = {USENIX Association}, month = jul }