nemo-mbridge-perf-moe-dispatcher-selection

nemo-mbridge-perf-moe-dispatcher-selection is a skill for Claude Code, Codex from NVIDIA-NeMo/Megatron-Bridge. It costs 76 tokens per session (2,346 once invoked), scanned A, original, Apache-2.0.

A guide for choosing and testing how a mixture-of-experts model sends tokens between GPUs. It compares all-to-all, DeepEP, and HybridEP dispatchers for a fixed workload and runtime.

In plain words
What is it for?
Selecting a token dispatcher, running fair performance comparisons, checking backend and hardware support, and tracing MoE routing problems.
Why use it?
It helps identify a dispatcher that works correctly and performs well on the available hardware. It also helps diagnose crashes or slowdowns caused by dispatcher settings.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Selecting a token dispatcher, running fair performance comparisons, checking backend and hardware support, and tracing MoE routing problems.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nvidia-nemo/megatron-bridge/nemo-mbridge-perf-moe-dispatcher-selection
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add NVIDIA-NeMo/Megatron-Bridge --skill nemo-mbridge-perf-moe-dispatcher-selection
Clone the repo
git clone --depth 1 https://github.com/NVIDIA-NeMo/Megatron-Bridge

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for nemo-mbridge-perf-moe-dispatcher-selection

README.md
[![agentmods](https://agentmods.dev/badge/skills/nvidia-nemo/megatron-bridge/nemo-mbridge-perf-moe-dispatcher-selection/github.svg)](https://agentmods.dev/skills/nvidia-nemo/megatron-bridge/nemo-mbridge-perf-moe-dispatcher-selection)
Your own site
<a href="https://agentmods.dev/skills/nvidia-nemo/megatron-bridge/nemo-mbridge-perf-moe-dispatcher-selection"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/megatron-bridge/nemo-mbridge-perf-moe-dispatcher-selection/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for nemo-mbridge-perf-moe-dispatcher-selection

Your own site · 80×15
<a href="https://agentmods.dev/skills/nvidia-nemo/megatron-bridge/nemo-mbridge-perf-moe-dispatcher-selection"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/megatron-bridge/nemo-mbridge-perf-moe-dispatcher-selection.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,346 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00076 $0.02346
Opus 5 $0.00038 $0.01173
Sonnet 5 $0.00015 $0.00469
Haiku 4.5 $0.00008 $0.00235

Measured 12d ago against content hash 2a6fb1c401e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

nemo-mbridge-perf-moe-dispatcher-selection scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/nemo-mbridge-perf-moe-dispatcher-selection/SKILL.md · 232 lines

How it starts

The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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 Bring-up path Tuned candidates
H100 alltoall A/B DeepEP and HybridEP when installed; the current 16×H100 Qwen3 30B winner is HybridEP
B200 alltoall A/B DeepEP and HybridEP when supported by the target runtime
GB200 / GB300 NVL72 alltoall HybridEP is the strongest topology-informed candidate; compare DeepEP when available
Unknown alltoall Add one flex backend only after the correctness baseline is stable

Hardware narrows the candidate set; it does not select the winner. Hold the model, routing, batch shape, parallelism, overlap, graph scope, container, and timing window fixed during the comparison.

By EP degree

EP size Guidance
Small EP Dispatcher choice may be second-order; start with alltoall
Medium EP Profile first, then A/B the installed flex backends
Large EP Prioritize topology-aware candidates, but still require a matched A/B

On one NVL8 domain in BF16, treat alltoall and HybridEP as matched candidates: their throughput can be close once the full stack is held fixed. HybridEP is a high-priority tuning path, not a reason to skip the correctness baseline.

Model-Family Patterns

Workload Common best path Notes
DSV3 at large scale Measured snapshots use HybridEP on GB200/GB300 and DeepEP on H100 Revalidate against the target container and topology
Qwen3 235B Current H100 recipe uses alltoall plus overlap; measured GB200 snapshots use HybridEP Do not replace the current recipe from a hardware rule alone
Qwen3 30B Current canonical 16×H100 recipe uses HybridEP Direct counterexample to H100 → DeepEP mapping
Qwen3-Next Workload-dependent Precision, memory, PP layout, and kernels can change the ordering
MoE VLMs Start simple, then test HybridEP on GB200-class systems Vision workloads are sensitive to both memory and host overhead

Read the full file on GitHub · 232 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 232 lines · 76 tokens per session scan A 2a6fb1c401e4

Subscribe to this mod's changes

nemo-mbridge-perf-moe-dispatcher-selection is a skill published in the GitHub repository NVIDIA-NeMo/Megatron-Bridge (906 stars, last pushed today), licensed Apache-2.0. It adds 76 tokens to every session and 2,346 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

cli-eval

Create and run evaluation suites, watch live benchmark progress, view scorecards, compare model performance, and integrate eval runs with CI workflows from the CLI.

diegosouzapw/OmniRoute · 34 tokens

model-merging

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task…

davila7/claude-code-templates · 73 tokens

merger-model

Build accretion/dilution analysis for M&A transactions. Models pro forma EPS impact, synergy sensitivities, and purchase price allocation. Use when evaluating a potential acquisition, preparing merger consequences analysis for a pitch, or advising on deal terms. Triggers on "merger model", "accretion dilution", "M&A…

anthropics/financial-services · 87 tokens

darwinian-evolver

Evolve prompts/regex/SQL/code with Imbue's evolution loop.

NousResearch/hermes-agent · 22 tokens

validate

Validate Semantica pipelines, extraction quality, graph schemas, and ontology consistency. Returns structured error/warning checklists. Uses PipelineValidator, PipelineBuilder.validatepipeline(), GraphValidator, and OntologyValidator. Sub-commands: pipeline, step, dependencies, extraction, graph, ontology, performance.

semantica-agi/semantica · 0 tokens

launching-evals

Run, monitor, analyze, and debug LLM evaluations via nemo-evaluator-launcher. Covers running evaluations, checking status and live progress, debugging failed runs, exporting artifacts and logs, and analyzing results. ALWAYS triggers on mentions of running evaluations, checking progress, debugging failed evals…

NVIDIA/Model-Optimizer · 115 tokens