@article{asurveyoninferenceenginesforlarge, title = {A Survey on Inference Engines for Large Language Models: Perspectives on Optimization and Efficiency}, author = {Sihyeong Park and Sungryeol Jeon and Chaelyn Lee and Seokhun Jeon and Byung-soo Kim and Jemin Lee}, year = {2025}, eprint = {2505.01658}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.01658v2}, }