@misc{stojkovic2024towards, title={Towards Greener LLMs: Bringing Energy-Efficiency to the Forefront of LLM Inference}, author={Jovan Stojkovic and Esha Choukse and Chaojie Zhang and Inigo Goiri and Josep Torrellas}, year={2024}, eprint={2403.20306}, archivePrefix={arXiv}, primaryClass={cs.AI}, url={https://arxiv.org/abs/2403.20306} }