[2606.02982] DriftSched: Adaptive QoS-Aware Scheduling under Runtime Token Drift for Multi-Tenant GPU Inference
![[2606.02982] DriftSched: Adaptive QoS-Aware Scheduling under Runtime Token Drift for Multi-Tenant GPU Inference](/static/img/curated/desks/afbytes-us.png)
AI disclosure
Summary
Abstract page for arXiv paper 2606.02982: DriftSched: Adaptive QoS-Aware Scheduling under Runtime Token Drift for Multi-Tenant GPU Inference