@article{tapasthermalandpowerawareschedulingfor,
  title = {TAPAS: Thermal- and Power-Aware Scheduling for LLM Inference in Cloud Platforms},
  author = {Jovan Stojkovic and Chaojie Zhang and Íñigo Goiri and Esha Choukse and Haoran Qiu and Rodrigo Fonseca and Josep Torrellas and Ricardo Bianchini},
  year = {2025},
  eprint = {2501.02600},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2501.02600v1},
}