# Tu(r)ning AI Green: Exploring Energy Efficiency Cascading with Orthogonal Optimizations

arXiv: https://arxiv.org/abs/2506.18289 · HTML: https://mlsanity.com/paper/2506.18289/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 21 references that are in the map.
- First posted on arXiv 23 Jun 2025.

## Builds on (most cited first, 8 of 8)

- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [Mixed Precision Training](https://mlsanity.com/paper/1710.03740/) (2017)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [Zeus: Understanding and Optimizing GPU Energy Consumption of DNN Training](https://mlsanity.com/paper/2208.06102/) (2022)
- [Dated Data: Tracing Knowledge Cutoffs in Large Language Models](https://mlsanity.com/paper/2403.12958/) (2024)
- [Carbon-Aware Computing for Datacenters](https://mlsanity.com/paper/2106.11750/) (2021)
- [Greening AI-enabled Systems with Software Engineering: A Research Agenda for Environmentally Sustainable AI Practices](https://mlsanity.com/paper/2506.01774/) (2025)

## Built on by (most cited first, 2 of 2)

- [Towards Green AI: Decoding the Energy of LLM Inference in Software Development](https://mlsanity.com/paper/2602.05712/) (2026)
- [Characterizing Performance-Energy Trade-offs of Large Language Models in Multi-Request Workflows](https://mlsanity.com/paper/2604.09611/) (2026)

## Abstract (arXiv)

AI's exponential growth intensifies computational demands and energy challenges. While practitioners employ various optimization techniques, that we refer as "knobs" in this paper, to tune model efficiency, these are typically afterthoughts and reactive ad-hoc changes applied in isolation without understanding their combinatorial effects on energy efficiency. This paper emphasizes on treating energy efficiency as the first-class citizen and as a fundamental design consideration for a compute-intensive pipeline. We show that strategic selection across five AI pipeline phases (data, model, training, system, inference) creates cascading efficiency. Experimental validation shows orthogonal combinations reduce energy consumption by up to 94.6% while preserving 95.95% of the original F1 score of non-optimized pipelines. This curated approach provides actionable frameworks for informed sustainable AI that balance efficiency, performance, and environmental responsibility.