2 papers
cs.DC2026
ViBE: Co-Optimizing Workload Skew and Hardware Variability for MoE Serving
Seokjin Go, Marko Scrbak, Ephrem Wu +2
In distributed Mixture-of-Experts (MoE) inference, input-dependent token routing interacts with GPU performance variability to create persistent stragglers under synchronized execu…
cs.DC2026
Power Aware Dynamic Reallocation For Inference
Yiwei Jiang, Sangeeta Chowdhary, Nathaniel Morris +3
Disaggregation has emerged as a powerful strategy for optimizing large language model (LLM) inference by separating compute-intensive prefill and memory-bound decode phases across…