@inproceedings{wu2026fastdllm,
  title = {{Fast-dLLM}: Training-free Acceleration of Diffusion {LLM} by Enabling {KV} Cache and Parallel Decoding},
  author = {Chengyue Wu and Hao Zhang and Shuchen Xue and Zhijian Liu and Shizhe Diao and Ligeng Zhu and Ping Luo and Song Han and Enze Xie},
  year = {2026},
  month = {April},
  booktitle = {International Conference on Learning Representations (ICLR)},
  eprint = {2505.22618},
  archiveprefix = {arXiv},
}
