Copertina

From Prompts to Power: Measuring the Energy Footprint of LLM Inference

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Caravaca, Francisco, Cuevas, Ángel, Cuevas, Rubén
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Green Prompting: Characterizing Prompt-driven Energy Costs of LLM Inference
di: Adamska, Marta, et al.
Pubblicazione: (2025)

LLMCO2: Advancing Accurate Carbon Footprint Prediction for LLM Inferences
di: Fu, Zhenxiao, et al.
Pubblicazione: (2024)

AIMeter: Measuring, Analyzing, and Visualizing Energy and Carbon Footprint of AI Workloads
di: Huang, Hongzhen, et al.
Pubblicazione: (2025)

Refinement Provenance Inference: Detecting LLM-Refined Training Prompts from Model Behavior
di: Yin, Bo, et al.
Pubblicazione: (2026)

Evaluating LLM Safety Under Repeated Inference via Accelerated Prompt Stress Testing
di: Broadwater, Keita
Pubblicazione: (2026)

The ML.ENERGY Benchmark: Toward Automated Inference Energy Measurement and Optimization
di: Chung, Jae-Won, et al.
Pubblicazione: (2025)

A TinyML Reinforcement Learning Approach for Energy-Efficient Light Control in Low-Cost Greenhouse Systems
di: Salem, Mohamed Abdallah, et al.
Pubblicazione: (2025)

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

Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign Prompts
di: Wu, Zhaomin, et al.
Pubblicazione: (2025)

PromptAudit: Auditing Prompt Sensitivity in LLM-Based Vulnerability Detection
di: Camarato, Steffen J., et al.
Pubblicazione: (2026)

Auto-Prompt Ensemble for LLM Judge
di: Li, Jiajie, et al.
Pubblicazione: (2025)

Thermodynamic Focusing for Inference-Time Search: Practical Methods for Target-Conditioned Sampling and Prompted Inference
di: Zhang, Zhan
Pubblicazione: (2025)

Multi-LLM Adaptive Conformal Inference for Reliable LLM Responses
di: Noh, Kangjun, et al.
Pubblicazione: (2026)

Soft Prompts for Evaluation: Measuring Conditional Distance of Capabilities
di: Nordby, Ross
Pubblicazione: (2025)

AI-Powered Bayesian Inference
di: O'Hagan, Sean, et al.
Pubblicazione: (2025)

eFedLLM: Efficient LLM Inference Based on Federated Learning
di: Ding, Shengwen, et al.
Pubblicazione: (2024)

WebLLM: A High-Performance In-Browser LLM Inference Engine
di: Ruan, Charlie F., et al.
Pubblicazione: (2024)

Operationalizing Data Minimization for Privacy-Preserving LLM Prompting
di: Zhou, Jijie, et al.
Pubblicazione: (2025)

RAP: Runtime Adaptive Pruning for LLM Inference
di: Liu, Huanrong, et al.
Pubblicazione: (2025)

SDQ: Sparse Decomposed Quantization for LLM Inference
di: Jeong, Geonhwa, et al.
Pubblicazione: (2024)

Tiny Reinforcement Learning for Quadruped Locomotion using Decision Transformers
di: Akgün, Orhan Eren, et al.
Pubblicazione: (2024)

Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems
di: Ross, Brendan Leigh, et al.
Pubblicazione: (2025)

Making AI Less "Thirsty": Uncovering and Addressing the Secret Water Footprint of AI Models
di: Li, Pengfei, et al.
Pubblicazione: (2023)

CSAttention: Centroid-Scoring Attention for Accelerating LLM Inference
di: Song, Chuxu, et al.
Pubblicazione: (2026)

Ecosystem Graphs: The Social Footprint of Foundation Models
di: Bommasani, Rishi, et al.
Pubblicazione: (2023)

Align-Pro: A Principled Approach to Prompt Optimization for LLM Alignment
di: Trivedi, Prashant, et al.
Pubblicazione: (2025)

DNN Memory Footprint Reduction via Post-Training Intra-Layer Multi-Precision Quantization
di: Ghavami, Behnam, et al.
Pubblicazione: (2024)

TokenPowerBench: Benchmarking the Power Consumption of LLM Inference
di: Niu, Chenxu, et al.
Pubblicazione: (2025)

Decocted Experience Improves Test-Time Inference in LLM Agents
di: Shen, Maohao, et al.
Pubblicazione: (2026)

Optimal Bayesian Stopping for Efficient Inference of Consistent LLM Answers
di: Huang, Jingkai, et al.
Pubblicazione: (2026)

Towards Low-bit Communication for Tensor Parallel LLM Inference
di: Dong, Harry, et al.
Pubblicazione: (2024)

AdaBlock-dLLM: Semantic-Aware Diffusion LLM Inference via Adaptive Block Size
di: Lu, Guanxi, et al.
Pubblicazione: (2025)

Prompt-Tuned LLM-Augmented DRL for Dynamic O-RAN Network Slicing
di: Lotfi, Fatemeh, et al.
Pubblicazione: (2025)

Prediction-Powered Inference with Imputed Covariates and Nonuniform Sampling
di: Kluger, Dan M., et al.
Pubblicazione: (2025)

Free Energy Manifold: Score-Based Inference for Hybrid Bayesian Networks
di: Park, Cheol Young, et al.
Pubblicazione: (2026)

Active Inference Meeting Energy-Efficient Control of Parallel and Identical Machines
di: Yeganeh, Yavar Taheri, et al.
Pubblicazione: (2024)

A Technical Exploration of Causal Inference with Hybrid LLM Synthetic Data
di: Kim, Dana, et al.
Pubblicazione: (2025)

Inference-Time Computations for LLM Reasoning and Planning: A Benchmark and Insights
di: Parashar, Shubham, et al.
Pubblicazione: (2025)

Distribution-Calibrated Inference time compute for Thinking LLM-as-a-Judge
di: Dadkhahi, Hamid, et al.
Pubblicazione: (2025)

Accelerating LLM Inference Throughput via Asynchronous KV Cache Prefetching
di: Dong, Yanhao, et al.
Pubblicazione: (2025)