@misc{https://doi.org/10.48550/arxiv.2609.18112,
  doi = {10.48550/ARXIV.2609.18112},
  url = {https://arxiv.org/abs/2609.18112},
  author = {Bali, Dev and Ponnapalli, Soujanya and Wang, Yichuan and Crooks, Natacha and Shenker, Scott and Zaharia, Matei},
  keywords = {Distributed, Parallel, and Cluster Computing (cs.DC), Machine Learning (cs.LG), FOS: Computer and information sciences},
  title = {Token Latency Fairness: Performance Isolation for Multi-Tenant LLM Serving},
  publisher = {arXiv},
  year = {2026},
  copyright = {Creative Commons Attribution 4.0 International}
}