@article{infmllmefficientstreaminginferenceof,
  title = {Inf-MLLM: Efficient Streaming Inference of Multimodal Large Language Models on a Single GPU},
  author = {Zhenyu Ning and Jieru Zhao and Qihao Jin and Wenchao Ding and Minyi Guo},
  year = {2024},
  eprint = {2409.09086},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2409.09086v1},
}