Cheng Zhang

FastEEP: Fast Intra-Instance Elastic Scaling for Expert-Parallel MoE Serving

Large-scale expert parallelism (EP) has become the standard deployment configuration for Mixture-of-Experts (MoE) models in production. Meanwhile, the highly dynamic nature of LLM workloads requires providers to continuously adjust serving capacity to match fluctuating demand. Scaling MoE serving cannot be efficiently...