Copertina

Energy-Conscious LLM Decoding: Impact of Text Generation Strategies on GPU Energy Consumption

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Nik, Alireza, Riegler, Michael A., Halvorsen, Pål
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

A Comparative Study of Decoding Strategies in Medical Text Generation
di: Presacan, Oriana, et al.
Pubblicazione: (2025)

Defending against Stegomalware in Deep Neural Networks with Permutation Symmetry
di: Torpmann-Hagen, Birk, et al.
Pubblicazione: (2025)

Probabilistic Runtime Verification, Evaluation and Risk Assessment of Visual Deep Learning Systems
di: Torpmann-Hagen, Birk, et al.
Pubblicazione: (2025)

HEDGE: Hallucination Estimation via Dense Geometric Entropy for VQA with Vision-Language Models
di: Gautam, Sushant, et al.
Pubblicazione: (2025)

Point, Detect, Count: Multi-Task Medical Image Understanding with Instruction-Tuned Vision-Language Models
di: Gautam, Sushant, et al.
Pubblicazione: (2025)

Principal Components for Neural Network Initialization
di: Phan, Nhan, et al.
Pubblicazione: (2025)

Kvasir-VQA: A Text-Image Pair GI Tract Dataset
di: Gautam, Sushant, et al.
Pubblicazione: (2024)

Enhancing Structured-Data Retrieval with GraphRAG: Soccer Data Case Study
di: Sepasdar, Zahra, et al.
Pubblicazione: (2024)

Medico 2025: Visual Question Answering for Gastrointestinal Imaging
di: Gautam, Sushant, et al.
Pubblicazione: (2025)

Explainability of Machine Learning Models under Missing Data
di: Vo, Tuan L., et al.
Pubblicazione: (2024)

VideoHEDGE: Entropy-Based Hallucination Detection for Video-VLMs via Semantic Clustering and Spatiotemporal Perturbations
di: Gautam, Sushant, et al.
Pubblicazione: (2026)

Diffused Responsibility: Analyzing the Energy Consumption of Generative Text-to-Audio Diffusion Models
di: Passoni, Riccardo, et al.
Pubblicazione: (2025)

Benchmarking the Energy Savings with Speculative Decoding Strategies
di: Dutta, Rohit, et al.
Pubblicazione: (2026)

SoccerChat: Integrating Multimodal Data for Enhanced Soccer Game Understanding
di: Gautam, Sushant, et al.
Pubblicazione: (2025)

Energy Consumption in Parallel Neural Network Training
di: Huber, Philipp, et al.
Pubblicazione: (2025)

Reducing Inference Energy Consumption Using Dual Complementary CNNs
di: Kinnas, Michail, et al.
Pubblicazione: (2024)

Towards Green AI: Decoding the Energy of LLM Inference in Software Development
di: Solovyeva, Lola, et al.
Pubblicazione: (2026)

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

BuildEvo: Designing Building Energy Consumption Forecasting Heuristics via LLM-driven Evolution
di: Lin, Subin, et al.
Pubblicazione: (2025)

Deep Learning Models in Speech Recognition: Measuring GPU Energy Consumption, Impact of Noise and Model Quantization for Edge Deployment
di: Chakravarty, Aditya
Pubblicazione: (2024)

Watt Counts: Energy-Aware Benchmark for Sustainable LLM Inference on Heterogeneous GPU Architectures
di: Argerich, Mauricio Fadel, et al.
Pubblicazione: (2026)

Position: AI Security Policy Should Target Systems, Not Models
di: Riegler, Michael A., et al.
Pubblicazione: (2026)

LLM-Enhanced Energy Contrastive Learning for Out-of-Distribution Detection in Text-Attributed Graphs
di: Ma, Xiaoxu, et al.
Pubblicazione: (2026)

Energy-Efficient Wireless LLM Inference via Uncertainty and Importance-Aware Speculative Decoding
di: Park, Jihoon, et al.
Pubblicazione: (2025)

Automated Text Scoring in the Age of Generative AI for the GPU-poor
di: Ormerod, Christopher Michael, et al.
Pubblicazione: (2024)

Calliope: A TTS-based Narrated E-book Creator Ensuring Exact Synchronization, Privacy, and Layout Fidelity
di: Hammer, Hugo L., et al.
Pubblicazione: (2026)

Ground-Truthing AI Energy Consumption: Validating CodeCarbon Against External Measurements
di: Fischer, Raphael
Pubblicazione: (2025)

Modelling the 5G Energy Consumption using Real-world Data: Energy Fingerprint is All You Need
di: Chen, Tingwei, et al.
Pubblicazione: (2024)

Green MLOps to Green GenOps: An Empirical Study of Energy Consumption in Discriminative and Generative AI Operations
di: Sánchez-Mompó, Adrián, et al.
Pubblicazione: (2025)

Latenrgy: Model Agnostic Latency and Energy Consumption Prediction for Binary Classifiers
di: Pittman, Jason M.
Pubblicazione: (2024)

Conversational Agents for Building Energy Efficiency -- Advising Housing Cooperatives in Stockholm on Reducing Energy Consumption
di: Ghani, Shadaab, et al.
Pubblicazione: (2025)

SLO-aware GPU Frequency Scaling for Energy Efficient LLM Inference Serving
di: Kakolyris, Andreas Kosmas, et al.
Pubblicazione: (2024)

Promoting Sustainable Web Agents: Benchmarking and Estimating Energy Consumption through Empirical and Theoretical Analysis
di: Krupp, Lars, et al.
Pubblicazione: (2025)

Emergent Causality and the Foundation of Consciousness
di: Bennett, Michael Timothy
Pubblicazione: (2023)

Why Is Anything Conscious?
di: Bennett, Michael Timothy, et al.
Pubblicazione: (2024)

Exploring the Privacy-Energy Consumption Tradeoff for Split Federated Learning
di: Lee, Joohyung, et al.
Pubblicazione: (2023)

Dimensionality Reduction on IoT Monitoring Data of Smart Building for Energy Consumption Forecasting
di: Koutras, Konstantinos, et al.
Pubblicazione: (2025)

Small is Sufficient: Reducing the World AI Energy Consumption Through Model Selection
di: Barros, Tiago da Silva, et al.
Pubblicazione: (2025)

Kvasir-VQA-x1: A Multimodal Dataset for Medical Reasoning and Robust MedVQA in Gastrointestinal Endoscopy
di: Gautam, Sushant, et al.
Pubblicazione: (2025)

The Generative Energy Arena (GEA): Incorporating Energy Awareness in Large Language Model (LLM) Human Evaluations
di: Arriaga, Carlos, et al.
Pubblicazione: (2025)