Cover Image

Quantifying the Energy Consumption and Carbon Emissions of LLM Inference via Simulations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Özcan, Miray, Wiesner, Philipp, Weiß, Philipp, Kao, Odej
Format:	Preprint
Published:	2025
Subjects:	Distributed, Parallel, and Cluster Computing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Choosing the Right Battery Model for Data Center Simulations
by: Kilian, Paul, et al.
Published: (2025)

Carbon-Aware Quality Adaptation for Energy-Intensive Services
by: Wiesner, Philipp, et al.
Published: (2024)

Vessim: A Testbed for Carbon-Aware Applications and Systems
by: Wiesner, Philipp, et al.
Published: (2023)

Optimizing Microgrid Composition for Sustainable Data Centers
by: Irion, Julius, et al.
Published: (2025)

FedZero: Leveraging Renewable Excess Energy in Federated Learning
by: Wiesner, Philipp, et al.
Published: (2023)

Distributed LLM Pretraining During Renewable Curtailment Windows: A Feasibility Study
by: Wiesner, Philipp, et al.
Published: (2026)

Flora: Efficient Cloud Resource Selection for Big Data Processing via Job Classification
by: Will, Jonathan, et al.
Published: (2025)

Carbon-Aware Microservice Deployment for Optimal User Experience on a Budget
by: Kreutz, Kevin, et al.
Published: (2025)

What happens when nanochat meets DiLoCo?
by: Acker, Alexander, et al.
Published: (2025)

Demeter: Resource-Efficient Distributed Stream Processing under Dynamic Loads with Multi-Configuration Optimization
by: Geldenhuys, Morgan, et al.
Published: (2024)

On Software Ageing Indicators in OpenStack
by: Yazvinskyi, Yevhen, et al.
Published: (2024)

Predicting Dynamic Memory Requirements for Scientific Workflow Tasks
by: Bader, Jonathan, et al.
Published: (2023)

Strategies to Measure Energy Consumption Using RAPL During Workflow Execution on Commodity Clusters
by: Thamm, Philipp, et al.
Published: (2025)

Learning Process Energy Profiles from Node-Level Power Data
by: Bader, Jonathan, et al.
Published: (2025)

KS+: Predicting Workflow Task Memory Usage Over Time
by: Bader, Jonathan, et al.
Published: (2024)

QONNECT: A QoS-Aware Orchestration System for Distributed Kubernetes Clusters
by: Aslan, Haci Ismail, et al.
Published: (2025)

Daedalus: Self-Adaptive Horizontal Autoscaling for Resource Efficiency of Distributed Stream Processing Systems
by: Pfister, Benjamin J. J., et al.
Published: (2024)

Beyond Microservices: Testing Web-Scale RCA Methods on GPU-Driven LLM Workloads
by: Scheinert, Dominik, et al.
Published: (2026)

Falafels: A tool for Estimating Federated Learning Energy Consumption via Discrete Simulation
by: de Barochez, Andrew Mary Huet, et al.
Published: (2025)

Sizey: Memory-Efficient Execution of Scientific Workflow Tasks
by: Bader, Jonathan, et al.
Published: (2024)

Predicting the Performance of Scientific Workflow Tasks for Cluster Resource Management: An Overview of the State of the Art
by: Bader, Jonathan, et al.
Published: (2025)

Simulations between Strongly Sublinear MPC and Node-Capacitated Clique
by: Schneider, Philipp, et al.
Published: (2025)

Federated Learning over Connected Modes
by: Grinwald, Dennis, et al.
Published: (2024)

Hybrid Heterogeneous Clusters Can Lower the Energy Consumption of LLM Inference Workloads
by: Wilkins, Grant, et al.
Published: (2024)

Optimizing Memory Allocation in Distributed Clusters with Predictive Modeling
by: Bader, Jonathan, et al.
Published: (2026)

Offline Energy-Optimal LLM Serving: Workload-Based Energy Models for LLM Inference on Heterogeneous Systems
by: Wilkins, Grant, et al.
Published: (2024)

Checkpoint and Restart: An Energy Consumption Characterization in Clusters
by: Moran, Marina, et al.
Published: (2024)

Decentralized LLM Inference over Edge Networks with Energy Harvesting
by: Khoshsirat, Aria, et al.
Published: (2024)

The Impact of Process Competition on Energy Consumption: Analysis and Modeling
by: Campos, Eduardo Gomes, et al.
Published: (2026)

Where Do the Joules Go? Diagnosing Inference Energy Consumption
by: Chung, Jae-Won, et al.
Published: (2026)

Byzantine Fault Tolerant Protocols with Near-Constant Work per Node without Signatures
by: Schneider, Philipp
Published: (2025)

Breaking through the $Ω(n)$-space barrier: Population Protocols Decide Double-exponential Thresholds
by: Czerner, Philipp
Published: (2022)

Aging-aware CPU Core Management for Embodied Carbon Amortization in Cloud LLM Inference
by: Hewage, Tharindu B., et al.
Published: (2025)

LLM-Emu: Native Runtime Emulation of LLM Inference via Profile-Driven Sampling
by: Da, Wei, et al.
Published: (2026)

Mobile Cloud Computing in Healthcare Using Dynamic Cloudlets for Energy-Aware Consumption
by: Muniswamaiah, Manoj, et al.
Published: (2019)

EdgeShard: Efficient LLM Inference via Collaborative Edge Computing
by: Zhang, Mingjin, et al.
Published: (2024)

EMLIO: Minimizing I/O Latency and Energy Consumption for Large-Scale AI Training
by: Jamil, Hasibul, et al.
Published: (2025)

Understanding Power and Energy Utilization in Large Scale Production Physics Simulation Codes
by: Bertsch, Adam, et al.
Published: (2022)

Augur: Pre-Execution Energy Prediction for Workflow Tasks in Heterogeneous Clusters
by: West, Kathleen, et al.
Published: (2026)

Quantifying the Carbon Reduction of DAG Workloads: A Job Shop Scheduling Perspective
by: Bostandoost, Roozbeh, et al.
Published: (2025)