@article{enablingdisaggregatedmultistagemllminfer,
  title = {Enabling Disaggregated Multi-Stage MLLM Inference via GPU-Internal Scheduling and Resource Sharing},
  author = {Lingxiao Zhao and Haoran Zhou and Yuezhi Che and Dazhao Cheng},
  year = {2025},
  eprint = {2512.17574},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2512.17574},
}