@article{characterizingandoptimizingllminference,
  title = {Characterizing and Optimizing LLM Inference Workloads on CPU-GPU Coupled Architectures},
  author = {Prabhu Vellaisamy and Thomas Labonte and Sourav Chakraborty and Matt Turner and Samantika Sury and John Paul Shen},
  year = {2025},
  eprint = {2504.11750},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2504.11750v1},
}