@misc{azuka2024pilot, title={LLM-Pilot: Characterize and Optimize Performance of your LLM Inference Services}, author={Małgorzata Łazuka and Andreea Anghel and Thomas Parnell}, year={2024}, eprint={2410.02425}, archivePrefix={arXiv}, primaryClass={cs.DC}, url={https://arxiv.org/abs/2410.02425} }