Abhishek Vijaya Kumar, Gianni Antichi, Rachee Singh. Aqua: Network-Accelerated Memory Offloading for LLMs in Scale-Up GPU Domains. In Lieven Eeckhout, Georgios Smaragdakis, Katai Liang, Adrian Sampson, Martha A. Kim, Christopher J. Rossbach, editors, Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2, ASPLOS 2025, Rotterdam, Netherlands, 30 March 2025 - 3 April 2025. pages 48-62, ACM, 2025. [doi]
@inproceedings{KumarAS25,
title = {Aqua: Network-Accelerated Memory Offloading for LLMs in Scale-Up GPU Domains},
author = {Abhishek Vijaya Kumar and Gianni Antichi and Rachee Singh},
year = {2025},
doi = {10.1145/3676641.3715983},
url = {https://doi.org/10.1145/3676641.3715983},
researchr = {https://researchr.org/publication/KumarAS25},
cites = {0},
citedby = {0},
pages = {48-62},
booktitle = {Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2, ASPLOS 2025, Rotterdam, Netherlands, 30 March 2025 - 3 April 2025},
editor = {Lieven Eeckhout and Georgios Smaragdakis and Katai Liang and Adrian Sampson and Martha A. Kim and Christopher J. Rossbach},
publisher = {ACM},
isbn = {979-8-4007-1079-7},
}