Power Sloshing in Compound Servers for Large-Scale AI Inference Workloads
Published in 53rd IEEE/ACM International Symposium on Computer Architecture (ISCA 2026), 2026
Albert Cho, Jovan Stojkovic, Leonardo Piga, Abhishek Dhanotia, Sultan Mahmud Sajal, Gefei Zuo, Krishna Malladi, Devon Akers, Kalyan Subramanian, Shobhit Kanaujia, Alexandros Daglis
Insights on AI inference power consumption trends, with an example scheme to slosh power across components.
