Click Thru Demos

Service Provider

Videos showcasing workflows for service providers/operators

• Model Deployment

  ---

  Workflows to deploy and operate multi tenant deployments of GenAI models.

• Service Provider Dashboards

  Visualization and analytics of time series data related to end user usage of deployed models.

  ---

• Storage Namespace

  Workflows to create and manage locally available storage resource (backed by local, high speed Object storage) where the operator can upload model weights etc.

  ---

• Inference Endpoints

  Workflow to configure, deploy and operate OpenAI compatible API endpoints where end users can access one/many LLMs

  ---

• Compute Clusters

  Workflow to register Kubernetes clusters based data plane for model deployments

  ---

---

End User

Click through demos showcasing workflows for End Users of Customer Orgs

• Usage

  Workflows for end user usage of LLMs on service provider hosted inference endpoints.

  ---