Why it matters
EP is MoE-specific parallelism. Understanding shapes MoE design.
Advertisement
The architecture
Experts sharded across GPUs.
All-to-all: send tokens to their experts.
Compute experts locally.
All-to-all: send back.
Advertisement
How it works end to end
All-to-all: heavy communication.
Capacity factor: balance load.
Combine with DP + TP + PP.