https://jeromemaquoi.github.io/
In this first paper, our findings suggest a link between the energy consumption of the source code and the number of objects’ attributes created within that code.
📄 Preprint: shorturl.at/LwpXJ
#FSE2025 #DevOpsSustain2025
In this first paper, our findings suggest a link between the energy consumption of the source code and the number of objects’ attributes created within that code.
📄 Preprint: shorturl.at/LwpXJ
#FSE2025 #DevOpsSustain2025
In this first paper, our findings suggest a link between the energy consumption of the source code and the number of objects’ attributes created within that code.
📄 Preprint: shorturl.at/LwpXJ
#FSE2025 #DevOpsSustain2025
Up to 4.08 Wh — like charging your phone to 40%!
In our new study we tested 17 models & 9,000+ runs.
Other key finds:
⚡️ Model energy use varies up to 46x
📐 Resolution matters, prompts don't
🛠️ Quantization ≠ savings
📄 Preprint: lnkd.in/dKWWAETW
Up to 4.08 Wh — like charging your phone to 40%!
In our new study we tested 17 models & 9,000+ runs.
Other key finds:
⚡️ Model energy use varies up to 46x
📐 Resolution matters, prompts don't
🛠️ Quantization ≠ savings
📄 Preprint: lnkd.in/dKWWAETW
Vous avez embarqué sur Hello Quitte X, et nous vous en remercions. Comme nous l’avons expliqué lors de la soirée #HelloQuitteX du lundi #20Janvier, nous ne sommes pas encore passés à la phase 2 (activation de la reconnexion).
1/6
Vous avez embarqué sur Hello Quitte X, et nous vous en remercions. Comme nous l’avons expliqué lors de la soirée #HelloQuitteX du lundi #20Janvier, nous ne sommes pas encore passés à la phase 2 (activation de la reconnexion).
1/6