Agent skill · software engineering · nvidia
dynamo-router-starter
Start or patch Dynamo router modes and run router endpoint smoke checks. Use for round-robin, KV-aware, least-loaded, or device-aware routing setup; use recipe-runner for recipe deployment and troubleshoot for failure diagnosis.
Why this skill is useful
Adds specific commands and configurations for setting up and testing Dynamo router modes that the AI wouldn't reliably generate on its own.
What it needs
Requires kubectl, python installed locally. About 3k tokens when loaded. Last updated 2026-08-07. 2,816 stars on the source repository.
What this skill does
Dynamo Router Starter <!-- SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved. SPDX-License-Identifier: CC-BY-4.0 --> Purpose Make Dynamo routing feel easy by getting a baseline router mode running, enabling KV-aware routing when appropriate, and proving the endpoint works. Keep the user focused on exact commands and success signals, not router internals. Prerequisites Python 3.10+ with the dynamo package importable (python3 -m dynamo.frontend --help works). For Kubernetes runs: kubectl configured with access to the target namespace and a deployed Dynamo recipe. Network reachability to the frontend service (port-forward or direct). A model already loaded into at least one worker (/v1/models returns at least one entry). Required Inputs Collect or infer: local Python/CLI or Kubernetes recipe path desired mode: round-robin, kv, least-loaded, device-aware-weighted, direct, or random frontend port or Kubernetes frontend service whether workers publish KV events; if not, use approximate KV mode model name for smoke requests, if /v1/models cannot discover it Instructions 1. Establish A Baseline For local bring-up with already registered workers: For Kubernetes, inspect the selected recipe deploy.yaml and locate the frontend service. If the recipe is not already deployed, use dynamo-recipe-runner first. 2. Enable KV Routing For local frontend: For Kubernetes, patch only the frontend service env: If backend workers are not publishing KV cache events, set approximate mode instead of leaving the router waiting for events: 3. Smoke Test After port-forwarding the frontend service or starting local frontend, run: This must verify /v1/models and, when a model is discoverable, one /v1/chat/completions request. 4. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills nvidia/dynamo-router-starter