What is Expert Parallelism? Why does it exist? Where does it appear in Mixture of Experts (MoE)?
Draw or describe a visual model of Expert Parallelism. What does it look like conceptually?
How is Expert Parallelism different from related concepts in Mixture of Experts (MoE)? What are the trade-offs?
Explain Expert Parallelism in plain language using an analogy. Could a non-expert follow it?