Index of every page on this site: llms.txt
All skills
nvidia avatar

/dynamo-router-starter

@6b75e9e
by NVIDIA Corporationnvidia/skills4.1k stars
547
Run it yourself

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.

Use this Skill: https://skilld.dev/gh/nvidia/skills/dynamo-router-starter

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈63 tokens for metadata: the name and description. ≈1.3k when used: this file. ≈2.6k more on demand in 4 files.

Description uses 3.1% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈252 characters, or 3.1%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

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:

python3 -m dynamo.frontend --router-mode round-robin --http-port 8000

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:

python3 -m dynamo.frontend --router-mode kv --http-port 8000

For Kubernetes, patch only the frontend service env:

envs:
  - name: DYN_ROUTER_MODE
    value: kv

If backend workers are not publishing KV cache events, set approximate mode instead of leaving the router waiting for events:

envs:
  - name: DYN_ROUTER_USE_KV_EVENTS
    value: "false"

3. Smoke Test

After port-forwarding the frontend service or starting local frontend, run:

python3 scripts/check_router_health.py \
  --base-url http://127.0.0.1:8000

This must verify /v1/models and, when a model is discoverable, one /v1/chat/completions request.

4. Compare Modes Carefully

When comparing round-robin vs KV routing:

  • use the same model, workers, prompt set, concurrency, and sampling settings
  • send repeated-prefix prompts if demonstrating KV reuse
  • label the result as a smoke comparison unless enough benchmark samples were collected
  • do not claim throughput improvement from a single chat request

If the endpoint is unhealthy or workers are missing, switch to dynamo-troubleshoot.

Available Scripts

Script Purpose Arguments
scripts/check_router_health.py Smoke-test /v1/models and one chat completion against a Dynamo frontend --base-url, --retries, --timeout

Invoke via the agentskills.io run_script() protocol:

run_script("scripts/check_router_health.py", args=["--base-url", "http://127.0.0.1:8000"])

Examples

Local KV-routed frontend on port 8000, then smoke-test it:

python3 -m dynamo.frontend --router-mode kv --http-port 8000 &
python3 scripts/check_router_health.py --base-url http://127.0.0.1:8000

Kubernetes-deployed frontend reachable via port-forward:

kubectl port-forward svc/qwen-vllm-disagg-frontend 8000:8000 -n dynamo-demo &
python3 scripts/check_router_health.py --base-url http://127.0.0.1:8000 --retries 3

Equivalent through the agent protocol:

run_script("scripts/check_router_health.py", args=["--base-url", "http://127.0.0.1:8000", "--retries", "3"])

Output Contract

Return:

  • mode selected and why
  • local command or Kubernetes env patch
  • frontend service or URL
  • smoke-test result
  • any limitation, such as approximate KV mode or missing worker KV events
  • next command to run for a fuller comparison

Limitations

  • Smoke test is one chat completion; it is not a benchmark. Use dynamo-benchmark for throughput/latency numbers.
  • KV-aware mode without worker KV-event publication degrades to approximate mode; this skill flags but does not fix the underlying worker config.
  • Mode comparisons require matched workloads; cross-mode latency claims need separate benchmark runs.

Troubleshooting

Symptom Likely cause Next step
/v1/models returns empty list No worker registered with the frontend Verify worker pods are Ready; confirm they connect to the same etcd/NATS
Smoke chat request times out Frontend up, workers not serving Switch to dynamo-troubleshoot; inspect worker logs
KV mode hangs Workers do not publish KV cache events Set DYN_ROUTER_USE_KV_EVENTS=false (approximate mode)
Connection refused on port-forward Port-forward dropped or wrong service name Re-run port-forward; verify the frontend service name matches the recipe

Benchmark

See BENCHMARK.md for the NVCARPS-EVAL performance report (auto-generated by the NVSkills CI pipeline). To refresh, re-run /nvskills-ci on an upstream PR touching this skill.

References

  • Read references/router-modes.md for the compact mode/env map.
  • Use scripts/check_router_health.py for endpoint smoke tests.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 alert5mo3 checks · Risk SAFE
  • Gen Agent Trust Hub5mo

    The skill provides tools and instructions for configuring and testing Dynamo router modes. It uses standard CLI tools (Python, kubectl) and includes a health check script with safety checks for URL schemes. No malicious patterns were detected.

  • Socket5mo

    No alerts

  • Snyk5mo

    Risk: CRITICAL · 2 issues

Signed by skilld at 6b75e9e. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 6 months ago
Other metadata
metadata
{
  "author": "Dan Gil <dagil@nvidia.com>",
  "tags": [
    "dynamo",
    "router",
    "smoke-test",
    "bring-up"
  ]
}

README badge

README badge for nvidia/skills/dynamo-router-starter