StarkServe: A Framework for Elastic Serverless LLM Inference at the Extreme Edge.
Mingxuan Zhang, Xiaofeng Hou, Jiacheng Liu, Chang Liu, Xinkai Wang, Chao Li, Minyi Guo, Han Yang
Browse the full IWQoS paper archive.
Mingxuan Zhang, Xiaofeng Hou, Jiacheng Liu, Chang Liu, Xinkai Wang, Chao Li, Minyi Guo, Han Yang
Browse the full IWQoS paper archive.