Similar Items: Affinity Tailor: Dynamic Locality-Aware Scheduling at Scale
- FATE: Future-State-Aware Scheduling for Heterogeneous LLM Workflows
- Taming Request Imbalance: SLO-Aware Scheduling for Disaggregated LLM Inference
- Replication in Graph Partitioning and Scheduling Problems
- SAGA: Workflow-Atomic Scheduling for AI Agent Inference on GPU Clusters
- EdgeServing: Deadline-Aware Multi-DNN Serving at the Edge
- Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation