@inproceedings{ijcai2026p502,
  title     = {M-LoRA: Efficient Serving for Concurrent LoRA Adapters with Memory-Aware Speculative Scheduler on Single GPU},
  author    = {Li, Shaolong and Yang, Xiang and Qi, Qi and Sun, Haifeng and Zhuang, Zirui and He, Bo and Ning, Wanyi and Wang, Jingyu},
  booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-26}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Diego Calvanese},
  pages     = {4509--4517},
  year      = {2026},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2026/502},
  url       = {https://doi.org/10.24963/ijcai.2026/502},
}