nemo-mbridge-perf-moe-dispatcher-selection
Originally fromnvidia/skills
Installation
SKILL.md
MoE Dispatcher Selection Guide
Stable docs: @docs/training/moe-optimization.md Card: @skills/nemo-mbridge-perf-moe-dispatcher-selection/card.yaml
Quick Decision
By hardware
| Hardware | First choice | Why |
|---|---|---|
| H100 | DeepEP, if the runtime package is installed | Strong default for cross-node EP on Hopper |
| B200 | DeepEP, if the runtime package is installed | Good first choice unless a platform-specific HybridEP path is available |
| GB200 / GB300 NVL72 | HybridEP, if the runtime package is installed | Best fit for NVLink-domain-aware dispatch and lower memory pressure |
| Unknown or first bring-up | alltoall |
Easiest path for correctness and debugging |