Pith. sign in

REVIEW 3 cited by

Unveiling Environmental Impacts of Large Language Model Serving: A Functional Unit View

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2502.11256 v2 pith:54FAUDIW submitted 2025-02-16 cs.LG cs.ARcs.CL

Yanran Wu , Inez Hua , Yi Ding This is my paper · ORCID
classification cs.LGcs.ARcs.CL
keywords carbonemissionsenvironmentalmodelservingbasisfuelfunctional
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Large language models (LLMs) offer powerful capabilities but come with significant environmental impact, particularly in carbon emissions. Existing studies benchmark carbon emissions but lack a standardized basis for comparison across different model configurations. To address this, we introduce the concept of functional unit (FU) as a standardized basis and develop FUEL, the first FU-based framework for evaluating LLM serving's environmental impact. Through three case studies, we uncover key insights and trade-offs in reducing carbon emissions by optimizing model size, quantization strategy, and hardware choice, paving the way for more sustainable LLM serving. The code is available at https://github.com/jojacola/FUEL.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Energy Considerations of Large Language Model Inference and Efficiency Optimizations

    cs.CL 2025-04 conditional novelty 5.0 of 10

    Measuring LLM inference across workloads, frameworks, and GPUs shows that efficiency optimizations like vLLM and CUDA graphs can cut energy use by up to 73% versus an unoptimized PyTorch baseline.

  2. The Generative Energy Arena (GEA): Incorporating Energy Awareness in Large Language Model (LLM) Human Evaluations

    cs.AI 2025-07 reject novelty 4.0 of 10

    In a public LLM comparison arena, showing users that the larger model consumes more energy caused about 46% of users who preferred it to say they would switch to the smaller model.

  3. EnsembleCI: Ensemble Learning for Carbon Intensity Forecasting

    cs.LG 2025-05 conditional novelty 4.0 of 10

    An ensemble of LightGBM, CatBoost, and a neural network forecasts grid carbon intensity for 4 days and beats CarbonCast by about 20% average MAPE across 11 grids.

Pith tools