# Compute and Energy Consumption Trends in Deep Learning Inference

arXiv: https://arxiv.org/abs/2109.05472 · HTML: https://mlsanity.com/paper/2109.05472/

## Key facts

- Cited by 61 papers in the map (data through 14 Oct 2026).
- Builds on 58 of its 98 references that are in the map.
- First posted on arXiv 12 Sep 2021.

## Builds on (most cited first, 30 of 58)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism](https://mlsanity.com/paper/1909.08053/) (2019)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)

## Built on by (most cited first, 30 of 61)

- [Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives](https://mlsanity.com/paper/2311.18259/) (2023)
- [Power Hungry Processing: Watts Driving the Cost of AI Deployment?](https://mlsanity.com/paper/2311.16863/) (2023)
- [Compute Trends Across Three Eras of Machine Learning](https://mlsanity.com/paper/2202.05924/) (2022)
- [Convolutional Differentiable Logic Gate Networks](https://mlsanity.com/paper/2411.04732/) (2024)
- [Offline Energy-Optimal LLM Serving: Workload-Based Energy Models for LLM Inference on Heterogeneous Systems](https://mlsanity.com/paper/2407.04014/) (2024)
- [Brain-inspired learning in artificial neural networks: a review](https://mlsanity.com/paper/2305.11252/) (2023)
- [Mokey: Enabling Narrow Fixed-Point Inference for Out-of-the-Box Floating-Point Transformer Models](https://mlsanity.com/paper/2203.12758/) (2022)
- [Optimizing LLM Inference: Fluid-Guided Online Scheduling with Memory Constraints](https://mlsanity.com/paper/2504.11320/) (2025)
- [Federated Fine-Tuning of LLMs on the Very Edge: The Good, the Bad, the Ugly](https://mlsanity.com/paper/2310.03150/) (2023)
- [Unveiling Energy Efficiency in Deep Learning: Measurement, Prediction, and Scoring across Edge Devices](https://mlsanity.com/paper/2310.18329/) (2023)
- [Hybrid Heterogeneous Clusters Can Lower the Energy Consumption of LLM Inference Workloads](https://mlsanity.com/paper/2407.00010/) (2024)
- [Watt For What: Rethinking Deep Learning's Energy-Performance Relationship](https://mlsanity.com/paper/2310.06522/) (2023)
- [MLPerf Power: Benchmarking the Energy Efficiency of Machine Learning Systems from Microwatts to Megawatts for Sustainable AI](https://mlsanity.com/paper/2410.12032/) (2024)
- [MACP: Efficient Model Adaptation for Cooperative Perception](https://mlsanity.com/paper/2310.16870/) (2023)
- [Don't Complete It! Preventing Unhelpful Code Completion for Productive and Sustainable Neural Code Completion Systems](https://mlsanity.com/paper/2209.05948/) (2022)
- [TeenyTinyLlama: open-source tiny language models trained in Brazilian Portuguese](https://mlsanity.com/paper/2401.16640/) (2024)
- [Tucano: Advancing Neural Text Generation for Portuguese](https://mlsanity.com/paper/2411.07854/) (2024)
- [The Future of Consumer Edge-AI Computing](https://mlsanity.com/paper/2210.10514/) (2022)
- [The European AI Liability Directives -- Critique of a Half-Hearted Approach and Lessons for the Future](https://mlsanity.com/paper/2211.13960/) (2022)
- [Efficiency is Not Enough: A Critical Perspective of Environmentally Sustainable AI](https://mlsanity.com/paper/2309.02065/) (2023)
- [Measuring the Energy Consumption and Efficiency of Deep Neural Networks: An Empirical Analysis and Design Recommendations](https://mlsanity.com/paper/2403.08151/) (2024)
- [Green AI: A Preliminary Empirical Study on Energy Consumption in DL Models Across Different Runtime Infrastructures](https://mlsanity.com/paper/2402.13640/) (2024)
- [Towards Sustainable NLP: Insights from Benchmarking Inference Energy in Large Language Models](https://mlsanity.com/paper/2502.05610/) (2025)
- [HW-GPT-Bench: Hardware-Aware Architecture Benchmark for Language Models](https://mlsanity.com/paper/2405.10299/) (2024)
- [Verification methods for international AI agreements](https://mlsanity.com/paper/2408.16074/) (2024)
- [Chat2Map: Efficient Scene Mapping from Multi-Ego Conversations](https://mlsanity.com/paper/2301.02184/) (2023)
- [Characterizing and Optimizing LLM Inference Workloads on CPU-GPU Coupled Architectures](https://mlsanity.com/paper/2504.11750/) (2025)
- [Hyperdimensional Representation Learning for Node Classification and Link Prediction](https://mlsanity.com/paper/2402.17073/) (2024)
- [SFPrompt: Communication-Efficient Split Federated Fine-Tuning for Large Pre-Trained Models over Resource-Limited Devices](https://mlsanity.com/paper/2407.17533/) (2024)
- [Neural Networks with Quantization Constraints](https://mlsanity.com/paper/2210.15623/) (2022)

## Abstract (arXiv)

The progress of some AI paradigms such as deep learning is said to be linked to an exponential growth in the number of parameters. There are many studies corroborating these trends, but does this translate into an exponential increase in energy consumption? In order to answer this question we focus on inference costs rather than training costs, as the former account for most of the computing effort, solely because of the multiplicative factors. Also, apart from algorithmic innovations, we account for more specific and powerful hardware (leading to higher FLOPS) that is usually accompanied with important energy efficiency optimisations. We also move the focus from the first implementation of a breakthrough paper towards the consolidated version of the techniques one or two year later. Under this distinctive and comprehensive perspective, we study relevant models in the areas of computer vision and natural language processing: for a sustained increase in performance we see a much softer growth in energy consumption than previously anticipated. The only caveat is, yet again, the multiplicative factor, as future AI increases penetration and becomes more pervasive.