@inproceedings{2025_marlin,
  author={Elias Frantar and Roberto L. Castro and Jiale Chen and Torsten Hoefler and Dan Alistarh},
  title={{MARLIN: Mixed-Precision Auto-Regressive Parallel Inference on Large Language Models}},
  year={2025},
  month={Feb.},
  booktitle={PPoPP '25: Proceedings of the 30th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming},
  doi={10.1145/3710848.371087},
}