@article{whispermlareducinggpumemoryconsumptionof,
  title = {Whisper-MLA: Reducing GPU Memory Consumption of ASR Models based on MHA2MLA Conversion},
  author = {Sen Zhang and Jianguo Wei and Wenhuan Lu and Xianghu Yue and Wei Li and Qiang Li and Pengcheng Zhao and Ming Cai and Luo Si},
  year = {2026},
  eprint = {2603.00563},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.00563},
}