Expert Transfer Bottleneck in Edge MoE Prefill
During prefill, a prompt supplies hundreds to thousands of tokens to each layer. Although each token routes to only experts, the union of selections across the prompt typically activates nearly the entire expert set. When the full model exceeds GPU memory, almost the complete expert pool must therefore be streamed over the CPU–GPU interconnect during each prefill pass. Transfer time consequently scales with the model's total parameter footprint rather than its sparse per-token active path, causing multi-second I/O latency and GPU idle time under on-demand expert loading.
0
1
Tags
Prep Sessions
Edge-Native Mixture-of-Experts Serving with FreeToken @ University of Michigan - Ann Arbor
Ch.1 Edge Serving Bottlenecks and Dynamics - Edge-Native Mixture-of-Experts Serving with FreeToken @ University of Michigan - Ann Arbor
Prefill Transfer and Context Recomputation Challenges - Edge-Native Mixture-of-Experts Serving with FreeToken @ University of Michigan - Ann Arbor
Ch.2 Pipelining and State Caching Mechanisms - Edge-Native Mixture-of-Experts Serving with FreeToken @ University of Michigan - Ann Arbor
Pipelined Loading via Full-Layer Double Buffering - Edge-Native Mixture-of-Experts Serving with FreeToken @ University of Michigan - Ann Arbor
Learn After
Why does the prefill phase typically activate nearly the entire expert set in every layer, even though each individual token only selects a sparse subset of experts?
In edge MoE deployments where the model exceeds available GPU memory, prefill transfer time scales with the sparse active path rather than the total parameter footprint of the model.
In an edge MoE deployment where the model exceeds available VRAM, what operational state does the GPU enter during prefill, and what hardware transfer activity causes this condition?
Explain why edge deployments of Mixture-of-Experts (MoE) models face an expert transfer bottleneck during the prefill phase, detailing the interaction between prompt routing behavior and edge hardware constraints.
Match each edge MoE prefill operational concept to its accurate description:
Order the stages that produce an expert transfer bottleneck during edge MoE prefill:
Analyze why reducing per-token routing () fails to alleviate the expert transfer bottleneck for long prompts, and evaluate how prompt length (token count) influences the expert transfer overhead compared to per-token sparsity.
Pipelined Full-Layer Double Buffering in MoE Prefill