Power Hungry Processing: Watts Driving the Cost of AI Deployment?

Source: ArXiv.org


In your opinion, between a generalist AI model and a specialised AI model, which of the 2 AI models consumes the most energy? This was the question posed by researchers Alexandra Sasha LuccioniYacine Jernite and Emma Strubell.

Figure 1 - The 5 modalities examined in our study, with the number of parameters of each model on the x axis and the average amount of carbon emitted for 1000 inferences on the y axis.
NB: Both axes are in logarithmic scale.

To obtain the answer, the researchers analysed the consumption of generative AI models that performdifferent tasks

  • Text classification; 

  • Token classification; 

  • Extractive question answering; 

  • Masked language modeling; 

  • Text generation; 

  • Summarization; 

  • Image classification;

  • Object detection; 

  • Image captioning and image generation. 

 

For the software, the researchers used the CodeCarbon application (open-source software for measuring the energy impact of Python code). For the hardware, the researchers used a service from Amazon Web Service (AWS) based on an NVIDIA A100-SXM4-80GB GPU.


Previous
Previous

Green Algorithms: Quantifying the Carbon Footprint of Computation

Next
Next

Towards the systematic reporting of the energy and carbon footprints of machine learning