ModServe: Modality- and Stage-Aware Resource Disaggregation for Scalable Multimodal Model Serving.

Haoran Qiu, Anish Biswas, Zihan Zhao, Jayashree Mohan, Alind Khare, Esha Choukse, igo Goiri, Zeyu Zhang, Haiying Shen, Chetan Bansal, Ramachandran Ramjee, Rodrigo Fonseca

Browse the full CLOUD paper archive.