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 $k$ 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 ($k$) 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