@article{towardsefficientlargemultimodalmodel,
  title = {ModServe: Scalable and Resource-Efficient Large Multimodal Model Serving},
  author = {Haoran Qiu and Anish Biswas and Zihan Zhao and Jayashree Mohan and Alind Khare and Esha Choukse and Íñigo Goiri and Zeyu Zhang and Haiying Shen and Chetan Bansal and Ramachandran Ramjee and Rodrigo Fonseca},
  year = {2025},
  eprint = {2502.00937},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.00937v2},
}