phenomenon · first seen 10 Oct 2026
energy efficiency of LLM inference
Also: green AI, energy per token, joules per token, energy-efficient LLM inference, energy efficiency of AI inference, energy consumption of LLM inference, energy consumption of machine learning
Measuring and optimizing the energy and carbon cost of running large language model inference.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Energy-Aware Agentic Orchestration for Multi-Site Service DeploymentPapers · 10 Oct 2026 · Rodrigo Moreira, Alisson Chaves, Larissa F. Rodrigues Moreira, Tereza Carvalho,…
- Towards Green AI: Evaluating Energy Efficiency for Quantized LLM InferencePapers · 13 Oct 2026 · Petar Basta
- When Is Smaller Greener? Right-Sizing Language Models for Agentic AIPapers · 14 Oct 2026 · Sajid Siraj, Maria Barbati
- Energy Consumption Analysis of Discrete Diffusion and Autoregressive Language ModelsPapers · 14 Oct 2026 · Boris Ruf, Marcin Detyniecki
- Make the Adversary Spend More Energy: Generative Deception against Language-Model Attackers in Critical InfrastructurePapers · 20 Oct 2026 · Vlad Mihal, Hosam Alamleh, Alessandro Cantelli-Forti
- The Token-Energy Law of LLM Decode: Active Bytes and Realized Time Account for Joules per TokenPapers · 20 Oct 2026 · Chenxu Niu, Batuhan Sencer, Wei Zhang, Yong Chen
Latest sources
- Sustainable Federated Fine-Tuning with LoRA: Environmental Impact and Performance FootprintPapers · 12 Nov 2026 · Pedro Augusto Londe Ribeiro, Rodrigo Moreira, Larissa Ferreira Rodrigues Moreira…
- The SIMPLE Law for Energy Cost of LLM InferencePapers · 2 Nov 2026 · Hiari Pizzini Cavagna, Andrea Proia, Daniele Cesarini, Zeynep Kiziltan, Andrea B…
- The Real Cost of Context: Predicting Compute Time and Energy Consumption in LLM Prefill and Decode PhasesPapers · 29 Oct 2026 · Lars Krupp, Daniel Geißler, Francisco M. Calatrava-Nicolas, Stefan Gerd Fritsch…
- Green Code or Costly Code? Evaluating the Energy Costs of Iterative LLM-Based Code OptimizationsPapers · 23 Oct 2026 · Sadra Emami, Benjamin Weigell, Mohammad Reza Mousavi, Gunel Jahangirova, Hugo Ar…
- Generalized green and red concepts for artificial intelligence, big data, and information and communication technologies: Multidimensional framework and countermeasuresPapers · 22 Oct 2026 · Jinsong Wu, Yixin Xiao, Haowei Bi, Huamin Fang
- Joules-to-GDP: How Much Economic Value Do AI Systems Produce per Unit of Energy?Papers · 22 Oct 2026 · Amirreza Zeinali, Jon Saad-Falcon, Avanika Narayan, Mersad Abbasi, Jonathan S. H…
- The Token-Energy Law of LLM Decode: Active Bytes and Realized Time Account for Joules per TokenPapers · 20 Oct 2026 · Chenxu Niu, Batuhan Sencer, Wei Zhang, Yong Chen
- Make the Adversary Spend More Energy: Generative Deception against Language-Model Attackers in Critical InfrastructurePapers · 20 Oct 2026 · Vlad Mihal, Hosam Alamleh, Alessandro Cantelli-Forti
- Energy Consumption Analysis of Discrete Diffusion and Autoregressive Language ModelsPapers · 14 Oct 2026 · Boris Ruf, Marcin Detyniecki
- When Is Smaller Greener? Right-Sizing Language Models for Agentic AIPapers · 14 Oct 2026 · Sajid Siraj, Maria Barbati
- Towards Green AI: Evaluating Energy Efficiency for Quantized LLM InferencePapers · 13 Oct 2026 · Petar Basta
- Energy-Aware Agentic Orchestration for Multi-Site Service DeploymentPapers · 10 Oct 2026 · Rodrigo Moreira, Alisson Chaves, Larissa F. Rodrigues Moreira, Tereza Carvalho,…