Skill: NVIDIA RAG Blueprint
by NVIDIA
Deploy, configure and troubleshoot the NVIDIA RAG Blueprint from your agent — Docker Compose, Helm or library, with feature toggles for VLM, guardrails and agentic RAG.
NVIDIA's official skill for bringing up Dynamo inference routing — pick a router mode, enable KV-aware routing, and smoke-test the frontend endpoint before claiming anything works.
NVIDIA Dynamo distributes inference across a fleet of workers, and its router mode is the setting that decides whether that fleet is actually being used well. Round-robin is the safe baseline; KV-aware routing sends a request to the worker most likely to already hold its prefix in cache; least-loaded and device-aware weighted trade differently again. This skill from NVIDIA's verified skills catalogue gets an agent from nothing to a working, proven routing setup.
It covers both deployment shapes. Locally, that is python3 -m dynamo.frontend --router-mode ... on a chosen HTTP port. On Kubernetes, it patches only the frontend service's environment — DYN_ROUTER_MODE — rather than rewriting a recipe, and it knows the specific trap that catches people: if the backend workers are not publishing KV cache events, KV mode will sit and wait, so the skill sets DYN_ROUTER_USE_KV_EVENTS=false for approximate mode and tells you it has done so.
The part worth having is the discipline around results. Every bring-up ends with check_router_health.py, which verifies /v1/models and issues one real chat completion. The skill then explicitly forbids drawing a throughput conclusion from that single request: mode comparisons must hold model, workers, prompt set, concurrency and sampling constant, repeated-prefix prompts are required to demonstrate KV reuse, and anything short of a proper benchmark run must be labelled a smoke comparison. It also ships a symptom-to-cause troubleshooting table — empty /v1/models, hanging KV mode, dropped port-forwards — and hands off to dynamo-troubleshoot when the endpoint is genuinely unhealthy.
Every skill in NVIDIA's catalogue ships with a verifiable NVIDIA signature (skill.oms.sig), governance metadata, and an auto-generated benchmark report. Needs Python 3.10+ with the dynamo package, and kubectl access for Kubernetes runs.
Once installed, ask your agent something like:
"Switch our Dynamo frontend on the dynamo-demo namespace to KV-aware routing and prove the endpoint still serves a chat completion."
The instructions your agent loads, as published by NVIDIA.
by NVIDIA
Deploy, configure and troubleshoot the NVIDIA RAG Blueprint from your agent — Docker Compose, Helm or library, with feature toggles for VLM, guardrails and agentic RAG.
by NVIDIA
Inspects the host's hardware, OS, CUDA driver and existing tooling, recommends one Holoscan SDK install method with a reason, then hands off to the matching install skill.
by NVIDIA
Picks the right vLLM or SGLang runtime for your Jetson generation and JetPack version, then produces a working OpenAI-compatible serving command.
by NVIDIA
Trains, distils, quantises, evaluates, exports and runs inference for RT-DETR real-time object detection in NVIDIA TAO, routing training through AutoML hyperparameter search by default.