@article{fiddlercpugpuorchestrationforfast,
  title = {Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models},
  author = {Keisuke Kamahori and Tian Tang and Yile Gu and Kan Zhu and Baris Kasikci},
  year = {2024},
  eprint = {2402.07033},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.07033v3},
}