Characterizing Performance-Energy Trade-offs of Large Language Models in Multi-Request Workflows

• URL: http://arxiv.org/abs/2604.09611v1
• Date: Thu, 12 Mar 2026 10:10:37 GMT
• Title: Characterizing Performance-Energy Trade-offs of Large Language Models in Multi-Request Workflows
• Abstract summary: Large language models (LLMs) are increasingly used in applications forming multi-request systems.<n>They amplify latency and energy demand during inference.<n>This paper presents the first systematic characterization of performance-energy trade-offs in multi-request inference.
• Score: 0.8250374560598494
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) are increasingly used in applications forming multi-request workflows like document summarization, search-based copilots, and multi-agent programming. While these workflows unlock richer functionality, they also amplify latency and energy demand during inference. Existing measurement and benchmarking efforts either focus on assessing LLM inference systems or consider single-request evaluations, overlooking workflow dependencies and cross-request interactions unique to multi-request workflows. Moreover, the energy usage of such interdependent LLM calls remains underexplored. To address these gaps, this paper presents the first systematic characterization of performance-energy trade-offs in multi-request LLM inference. We develop four representative workloads capturing sequential, interactive, agentic, and composite patterns common in modern deployments. Using an NVIDIA A100 testbed with state-of-the-art serving systems (vLLM and Parrot), we analyze how key energy knobs affect latency, throughput, and component-level energy use. Our findings reveal batch size as the most impactful lever, though benefits are workload dependent. While optimal batching benefits workloads with large shared prompts, it is ineffective for sequential summarization and only partially effective for multi-agent coding. GPU power capping provides modest but predictable savings, while output length induces linear energy scaling with limited efficiency gains. We further show that engine-level optimizations in vLLM maintain higher GPU utilization and efficiency, especially for decode-heavy workloads, while Parrot's workflow-aware scheduling achieves lower energy consumption under strict power constraints. These findings offer actionable guidelines for developers and system operators designing performance- and energy-aware LLM serving systems in emerging multi-request workflows.

Related papers

• Hybrid Workflow Composition for Extreme-Scale Data Processing: A Case Study on the HL-LHC (Extended Version) [0.5156484100374059]
  This paper presents a novel simulation framework for characterizing the interplay between taskset granularity and system-level constraints.<n>Results show that hybrid composition strategies can yield up to 3.8x throughput increase and a 14.9x reduction in network overhead.
  arXiv  Detail & Related papers  (2026-07-29T13:07:31Z)
• Chimera: Latency- and Performance-Aware Multi-agent Serving for Heterogeneous LLMs [62.17306142810532]
  We present Chimera, a predictive scheduling system for multi-agent workflow serving on heterogeneous LLM clusters.<n>Chime traces the best latency, reducing end-to-end latency by 1.2--2.4$times$ and improving task performance by 8.0-9.5 percentage points on average over competitive baselines.
  arXiv  Detail & Related papers  (2026-03-23T17:01:42Z)
• Efficient LLM Serving for Agentic Workflows: A Data Systems Perspective [3.9457939396735573]
  Helium is a workflow-aware serving framework that models agentic workloads as query plans and treats LLM invocations as first-class operators.<n>Helium bridges classic query optimization principles with LLM serving, achieving up to 1.56x speedup over state-of-the-art agent serving systems.
  arXiv  Detail & Related papers  (2026-03-17T04:03:18Z)
• Parallelization Strategies for Dense LLM Deployment: Navigating Through Application-Specific Tradeoffs and Bottlenecks [6.447439020088275]
  Breakthroughs in AI have fueled an explosion of large language model (LLM)-powered applications.<n>Dense models continue to dominate because of their strong ability, scalability, ease of fine-tuning, and versatility across diverse tasks.<n>This paper investigates the workloads of two representative dense LLMs, focusing in particular on intra-node parallelization schemes.
  arXiv  Detail & Related papers  (2026-03-05T21:33:24Z)
• Eliminating Multi-GPU Performance Taxes: A Systems Approach to Efficient Distributed LLMs [61.953548065938385]
  We introduce the ''Three Taxes'' (Bulk Synchronous, Inter- Kernel Data Locality, and Kernel Launch Overhead) as an analytical framework.<n>We propose moving beyond the rigid BSP model to address key inefficiencies in distributed GPU execution.<n>We observe a 10-20% speedup in end-to-end latency over BSP-based approaches.
  arXiv  Detail & Related papers  (2025-11-04T01:15:44Z)
• Characterizing the Efficiency of Distributed Training: A Power, Performance, and Thermal Perspective [6.51239603014107]
  Large Language Models (LLMs) have pushed training workloads beyond the limits of single-node analysis.<n>We present a comprehensive characterization of LLM training across diverse real-world workloads and hardware platforms.
  arXiv  Detail & Related papers  (2025-09-12T16:05:07Z)
• Benchmarking Agentic Workflow Generation [80.74757493266057]
  We introduce WorfBench, a unified workflow generation benchmark with multi-faceted scenarios and intricate graph workflow structures.<n>We also present WorfEval, a systemic evaluation protocol utilizing subsequence and subgraph matching algorithms.<n>We observe that the generated can enhance downstream tasks, enabling them to achieve superior performance with less time during inference.
  arXiv  Detail & Related papers  (2024-10-10T12:41:19Z)
• FactorLLM: Factorizing Knowledge via Mixture of Experts for Large Language Models [50.331708897857574]
  We introduce FactorLLM, a novel approach that decomposes well-trained dense FFNs into sparse sub-networks without requiring any further modifications. FactorLLM achieves comparable performance to the source model securing up to 85% model performance while obtaining over a 30% increase in inference speed.
  arXiv  Detail & Related papers  (2024-08-15T16:45:16Z)
• Efficient Heterogeneous Large Language Model Decoding with Model-Attention Disaggregation [15.35494431928751]
  Transformer-based large language models (LLMs) exhibit impressive performance in generative tasks but also introduce significant challenges in real-world serving.<n>We introduce model-attention disaggregation to enhance the efficiency of LLM decoding.<n>We develop and deploy Lamina, an LLM inference system that incorporates model-attention disaggregation in a distributed heterogeneous cluster.
  arXiv  Detail & Related papers  (2024-05-03T02:15:15Z)
• Characterization of Large Language Model Development in the Datacenter [55.9909258342639]
  Large Language Models (LLMs) have presented impressive performance across several transformative tasks. However, it is non-trivial to efficiently utilize large-scale cluster resources to develop LLMs. We present an in-depth characterization study of a six-month LLM development workload trace collected from our GPU datacenter Acme.
  arXiv  Detail & Related papers  (2024-03-12T13:31:14Z)
• Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models [90.14693869269519]
  MoE LLMs can achieve higher performance with fewer parameters, but it is still hard to deploy them due to their immense parameter sizes. This paper mainly aims to enhance the deployment efficiency of MoE LLMs by introducing plug-and-play expert-level sparsification techniques.
  arXiv  Detail & Related papers  (2024-02-22T18:56:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.