@article{flashsvdmemoryefficientinferencewithstre,
  title = {FlashSVD: Memory-Efficient Inference with Streaming for Low-Rank Models},
  author = {Zishan Shao and Yixiao Wang and Qinsi Wang and Ting Jiang and Zhixu Du and Hancheng Ye and Danyang Zhuo and Yiran Chen and Hai Li},
  year = {2025},
  eprint = {2508.01506},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2508.01506},
}