@article{driftschedadaptiveqosawareschedulingunde, title = {DriftSched: Adaptive QoS-Aware Scheduling under Runtime Token Drift for Multi-Tenant GPU Inference}, author = {Kathiravan Palaniappan}, year = {2026}, eprint = {2606.02982}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.02982}, }