Offline energy-optimal llm serving: Workload-based energy models for llm inference on heterogeneous systems

G Wilkins, S Keshav, R Mortier - arXiv preprint arXiv:2407.04014, 2024 - arxiv.org
The rapid adoption of large language models (LLMs) has led to significant advances in
natural language processing and text generation. However, the energy consumed through …

[PDF][PDF] Carbon emissions in the tailpipe of generative AI

T Kneese, M Young - Harvard Data Science Review, 2024 - assets.pubpub.org
This essay responds to the call for exploring the wider societal risks and impacts of
generative AI, particularly its environmental costs. Through a review of the available …

TAPAS: Thermal-and Power-Aware Scheduling for LLM Inference in Cloud Platforms

J Stojkovic, C Zhang, Í Goiri, E Choukse, H Qiu… - arXiv preprint arXiv …, 2025 - arxiv.org
The rising demand for generative large language models (LLMs) poses challenges for
thermal and power management in cloud datacenters. Traditional techniques often are …

[PDF][PDF] Geographical Server Relocation: Opportunities and Challenges

Y Liu, P Li, D Wong, S Ren - Proceedings of HotCarbon, 2024 - hotcarbon.org
The enormous growth of AI computing has led to a surging demand for electricity. To stem
the resulting energy cost and environmental impact, this paper explores opportunities …

Learning-augmented decentralized online convex optimization in networks

P Li, J Yang, A Wierman, S Ren - … of the ACM on Measurement and …, 2024 - dl.acm.org
This paper studies learning-augmented decentralized online convex optimization in a
networked multi-agent system, a challenging setting that has remained under-explored. We …

Towards socially and environmentally responsible ai

P Li, Y Liu, J Yang, S Ren - arXiv preprint arXiv:2407.05176, 2024 - arxiv.org
The sharply increasing sizes of artificial intelligence (AI) models come with significant
energy consumption and environmental footprints, which can disproportionately impact …

The Unpaid Toll: Quantifying the Public Health Impact of AI

Y Han, Z Wu, P Li, A Wierman, S Ren - arXiv preprint arXiv:2412.06288, 2024 - arxiv.org
The surging demand for AI has led to a rapid expansion of energy-intensive data centers,
impacting the environment through escalating carbon emissions and water consumption …

(DRAFT) 如何藉由「以人為本」 進路實現國科會AI 科研發展倫理指南

JJ Lian - 2024 - philpapers.org
本文深入探討人工智慧(AI) 於實現共同福祉與幸福, 公平與非歧視, 理性公共討論及自主與控制
之倫理與正義重要性與挑戰. 以中央研究院LLM 事件及國家科學技術委員會(NSTC) AI …

Towards Environmentally Equitable AI

M Hajiesmaili, S Ren, RK Sitaraman… - arXiv preprint arXiv …, 2024 - arxiv.org
The skyrocketing demand for artificial intelligence (AI) has created an enormous appetite for
globally deployed power-hungry servers. As a result, the environmental footprint of AI …

[PDF][PDF] Online Workload Allocation and Energy Optimization in Large Language Model Inference Systems

G Wilkins - 2024 - grantwilkins.github.io
The rapid adoption of Large Language Models (LLMs) has furthered natural language
processing and helped text generation, question answering, and sentiment analysis …