Skip to main content

Deploy an endpoint

Deploy a model as a Workbench inference endpoint.

Deploy an endpoint

Deploy an endpoint when you want to serve a model behind an authenticated HTTP URL. Workbench supports LLM and predictive endpoints, multiple model sources, and runtime tuning through inference presets.

Deploy a model as a Workbench inference endpoint using the three-step endpoint wizard.

TimeAbout 5 minutes, plus model startup time
You will needA model source and at least one inference preset/runtime
OutcomeA running inference endpoint with a request URL

Open KServe endpoints

Click Workbench in the left sidebar, then click Serve > KServe > Inferences.

Start the endpoint wizard

Click Deploy endpoint. The Deploy Inference Endpoint modal opens.

Complete Identity

Enter an Endpoint name and optional Description.

Complete Model source

Select a source type and fill in the matching fields.

Source typeWhat you provide
S3Bucket and optional prefix.
HuggingFaceRepository, optional revision, and optional HuggingFace secret for gated models.
PVCClaim name and optional path.
Model RegistryRegistered model and version.
Custom URIContainer or model URI.

For non-HuggingFace sources, also choose the endpoint Kind: LLM or Predictive. HuggingFace sources use runtime suggestions to infer the kind when possible.

Complete Tuning

Select an inference Preset, Runtime, and Framework. Presets fill in sizing values such as CPU, memory, GPU count, compute pool, configuration defaults, and replica bounds.

Deploy

Click Deploy endpoint.

Open endpoint details

The endpoint appears in the Inferences list. Click the row to open the detail page, view status, copy the request URL, and inspect related components.

Success looks like this: the endpoint reaches Running, at least one predictor replica is ready, and requests to the displayed URL return responses.

LLMs can report an active Kubernetes service before weights are fully loaded into GPU memory. If requests time out immediately after deployment, check the endpoint detail page and logs before changing the configuration.

Ask AI
Ask a question about Vantage Compute...