SyncIntellects: Orchestrating LLM Inference with Progressive Prediction and QoS-Friendly Control.
Xue Lin, Zhibo Zhang, Peining Yue, Haoran Li, Jin Zhang, Baoyu Fan, Huayou Su, Xiaoli Gong
Browse the full IWQoS paper archive.
Xue Lin, Zhibo Zhang, Peining Yue, Haoran Li, Jin Zhang, Baoyu Fan, Huayou Su, Xiaoli Gong
Browse the full IWQoS paper archive.