Hermes: Efficient Serving of LLM Applications with Probabilistic Demand Modeling
ACM Transactions on Architecture and Code Optimization · 30.06.2026 · 23 (2) · 1-25
DOI: 10.1145/3803390 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Architecture and Code Optimization, online erschienen am 27.06.2026. Verfasst von Yifei Liu und 10 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 88 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Applications based on Large Language Models (LLMs) contain a series of tasks to address real-world problems with boosted capability, which have dynamic demand volumes on diverse backends. Existing serving systems treat the resource demands of LLM applications as a blackbox, compromising end-to-end efficiency due to improper queuing order and backend warm up latency. We find that the resource demands of LLM applications can be modeled in a general and accurate manner with Probabilistic Demand Graph (PDGraph). We then propose Hermes, which leverages PDGraph for efficient serving of LLM applications. Confronting probabilistic demand description, Hermes applies the Gittins policy to determine the scheduling order that can minimize the average application completion time. It also uses the PDGraph model to help prewarm cold backends at proper moments. Experiments with diverse LLM applications confirm that Hermes can effectively improve the application serving efficiency, reducing the average completion time by over 70% and the P95 completion time by over 80%.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Liu, Y., Gan, Z., Gan, Z., Wang, W., Chen, C., Shan, Y., Chen, X., Han, Z., Zhu, Y., Sun, S., & Guo, M. (2026). Hermes: Efficient Serving of LLM Applications with Probabilistic Demand Modeling. ACM Transactions on Architecture and Code Optimization, 23(2), 1-25. https://doi.org/10.1145/3803390
Vancouver
Liu Y, Gan Z, Gan Z, Wang W, Chen C, Shan Y, et al. Hermes: Efficient Serving of LLM Applications with Probabilistic Demand Modeling. ACM Transactions on Architecture and Code Optimization. 2026;23(2):1-25. doi:10.1145/3803390
BibTeX
@article{Liu2026,
author = {Liu, Yifei and Gan, Zuo and Gan, Zhenghao and Wang, Weiye and Chen, Chen and Shan, Yizhou and Chen, Xusheng and Han, Zhenhua and Zhu, Yifei and Sun, Shixuan and Guo, Minyi},
title = {Hermes: Efficient Serving of LLM Applications with Probabilistic Demand Modeling},
journal = {ACM Transactions on Architecture and Code Optimization},
year = {2026},
volume = {23},
number = {2},
pages = {1--25},
doi = {10.1145/3803390}
}
EUVIMED