Aegaeon: Effective GPU Pooling for Concurrent LLM Serving on the Market

Yuxing Xiang, Xue Li, Kun Qian, Yufan Yang, Diwen Zhu, Wenyuan Yu, Ennan Zhai, Xuanzhe Liu, Xin Jin, Jingren Zhou

Published: 13 Oct 2025, Last Modified: 27 Jan 2026CrossrefEveryoneRevisionsCC BY-SA 4.0
Loading