VoltanaLLM: Feedback-Driven Frequency Control and State-Space Routing for Energy-Efficient LLM Serving

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yu, Jiahuan, Taneja, Aryan, Lin, Junfeng, Zhang, Minjia
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916948618510336
author Yu, Jiahuan
Taneja, Aryan
Lin, Junfeng
Zhang, Minjia
author_facet Yu, Jiahuan
Taneja, Aryan
Lin, Junfeng
Zhang, Minjia
contents Modern Large Language Model (LLM) serving systems increasingly support interactive applications, like real-time chat assistants, code generation tools, and agentic workflows. However, the soaring energy cost of LLM inference presents a growing challenge for sustainable and cost-effective deployment. This paper introduces VoltanaLLM, a system for SLO-aware, energy-efficient LLM serving, built from a control theory perspective. VoltanaLLM co-designs frequency scaling and request routing in emerging prefill/decode disaggregated architectures, leveraging their decoupled execution to enable fine-grained phase-specific control. It consists of a feedback-driven frequency controller that dynamically adapts GPU frequency for prefill and decode phases, and a state-space router that explores routing decisions across frequency-scaled instances to minimize energy under latency constraints. We implement VoltanaLLM in SGLang and evaluate its performance over multiple state-of-the-art LLMs and real-world datasets. The results demonstrate that VoltanaLLM achieves up to 36.3% energy savings while maintaining near-perfect SLO attainment rate, paving the way for sustainable and intelligent LLM serving. Code of VoltanaLLM is open-sourced on GitHub: https://github.com/Supercomputing-System-AI-Lab/VoltanaLLM.
format Preprint
id arxiv_https___arxiv_org_abs_2509_04827
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VoltanaLLM: Feedback-Driven Frequency Control and State-Space Routing for Energy-Efficient LLM Serving
Yu, Jiahuan
Taneja, Aryan
Lin, Junfeng
Zhang, Minjia
Distributed, Parallel, and Cluster Computing
Artificial Intelligence
Machine Learning
Modern Large Language Model (LLM) serving systems increasingly support interactive applications, like real-time chat assistants, code generation tools, and agentic workflows. However, the soaring energy cost of LLM inference presents a growing challenge for sustainable and cost-effective deployment. This paper introduces VoltanaLLM, a system for SLO-aware, energy-efficient LLM serving, built from a control theory perspective. VoltanaLLM co-designs frequency scaling and request routing in emerging prefill/decode disaggregated architectures, leveraging their decoupled execution to enable fine-grained phase-specific control. It consists of a feedback-driven frequency controller that dynamically adapts GPU frequency for prefill and decode phases, and a state-space router that explores routing decisions across frequency-scaled instances to minimize energy under latency constraints. We implement VoltanaLLM in SGLang and evaluate its performance over multiple state-of-the-art LLMs and real-world datasets. The results demonstrate that VoltanaLLM achieves up to 36.3% energy savings while maintaining near-perfect SLO attainment rate, paving the way for sustainable and intelligent LLM serving. Code of VoltanaLLM is open-sourced on GitHub: https://github.com/Supercomputing-System-AI-Lab/VoltanaLLM.
title VoltanaLLM: Feedback-Driven Frequency Control and State-Space Routing for Energy-Efficient LLM Serving
topic Distributed, Parallel, and Cluster Computing
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2509.04827