vix.ing · top · new · best · stats · spec

Du, Chuheng

  1. TokenFlow: Responsive LLM Text Streaming Serving under Request Burst via Preemptive Scheduling
    2025/10/03 by Chen, Junyi, Du, Chuheng, Liu, Renyuan +6 · 2 citations
    #FOS: Computer and information sciences #Machine Learning (cs.LG)