Runtimes¶

Tempo runtimes provide the core functionality to deploy a tempo Model. They must provide concrete implementations for the following functionality:

Method

Action

deploy_local

deploy a model to the product’s local runtime

deploy_remote

deploy a model to the product’s remote runtime

undeploy

undeploy a model

wait_ready

wait for a deployed model to be ready

endpoint

get the URL for the deployed model so it can be called

manifest

optionally get the Kubernetes declarative yaml for the model

The Runtimes defined within Tempo are:

Runtime

Infrastructure Target

Example

SeldonDockerRuntime

deploy Tempo models to Docker

Custom model

SeldonKubernetesRuntime

deploy Tempo models to a Kubernetes cluster with Seldon Core installed

Multi-model

KFServingKubernetesRuntime

deploy Tempo models to a Kubernetes cluster with KFServing installed

KFServing

SeldonDeployRuntime

deploy Tempo models to a Kubernetes cluster with Seldon Deploy installed