> For clean Markdown content of this page, append .md to this URL. For the complete documentation index, see https://docs.nvidia.com/dynamo/llms.txt. For full content including API reference and SDK examples, see https://docs.nvidia.com/dynamo/llms-full.txt.

# Model Deployment

A **DynamoGraphDeployment (DGD)** is the Kubernetes entry point for serving a model
with Dynamo. It defines the frontend and model workers, their images and resources,
and how requests flow through the inference graph. When you apply a DGD, the Dynamo
operator creates and manages the underlying Kubernetes workloads and services.

The DGD is the deployment artifact that ultimately serves traffic, regardless of
whether you start from a tuned manifest, copy a template, generate one, or write the
resource directly.

## Create a DGD

Choose the starting point that best matches your model, hardware, and desired level
of control.

#### [Start from a Recipe](/dynamo/dev/recipes/browse)

Use a tuned DGD manifest when a recipe matches your model, backend, GPU, and serving topology.

#### [Copy a Backend Template](/dynamo/dev/recipes/kubernetes-templates/dgd/v-llm)

Start from an aggregated, disaggregated, or multinode manifest for [vLLM](/dynamo/dev/recipes/kubernetes-templates/dgd/v-llm), [SGLang](/dynamo/dev/recipes/kubernetes-templates/dgd/sg-lang), or [TensorRT-LLM](/dynamo/dev/recipes/kubernetes-templates/dgd/tensor-rt-llm).

#### [Auto Deployment](/dynamo/dev/kubernetes/auto-deployment/overview)

Learn when to use DGDR and how the Profiler and Planner generate and operate a DGD.

#### [Write a DGD Directly](/dynamo/dev/kubernetes/model-deployment/deploy-with-dgd)

Define components, parallelism, replicas, and Kubernetes settings for full control over the deployment.

## Choose a Deployment Topology

Start with aggregated serving when one worker can handle both prompt processing and
token generation. For more demanding models and workloads, use these guides to split,
size, or distribute the deployment.

#### [Disaggregated Serving](/dynamo/dev/kubernetes/disaggregated-serving/overview)

Run prefill and decode in separate worker pools so you can size and scale each phase independently.

#### [Size with AIConfigurator](/dynamo/dev/kubernetes/disaggregated-serving/size-with-ai-configurator)

Evaluate parallelism and replica configurations against your hardware and latency target.

#### [Multinode Deployments](/dynamo/dev/kubernetes/model-deployment/multinode-deployments)

Run workers that require more GPUs than a single Kubernetes node provides.