Product Selector

Fusion 5.9
    Fusion 5.9

    Create Ray Model Deployment

    Table of Contents

    Fusion 5.9.12 uses Ray to deploy machine learning (ML) models into production.

    This job deploys a Ray deployment into the Fusion cluster.

    To create the job, sign in to Fusion and click Collections > Jobs. Then click Add+ and in the Model Deployment Jobs section, select Create Ray Model Deployment.

    You can enter basic and advanced parameters to configure the job. If the field has a default value, it is populated when you click to add the job. To enter advanced parameters in the UI, click Advanced.

    For detailed information to deploy available Fusion Seldon models, see the:

    Configuration properties

    Deploys a Ray Model into the Fusion cluster

    id - stringrequired

    The ID for this job. Used in the API to reference this job. Allowed characters: a-z, A-Z, dash (-) and underscore (_)

    <= 63 characters

    Match pattern: [a-zA-Z][_\-a-zA-Z0-9]*[a-zA-Z0-9]?

    sparkConfig - array[object]

    Provide additional key/value pairs to be injected into the training JSON map at runtime. Values will be inserted as-is, so use " to surround string values

    object attributes:{key required : {
     display name: Parameter Name
     type: string
    }    value : {
     display name: Parameter Value
     type: string
    }    }

    writeOptions - array[object]

    Options used when writing output to Solr or other sources

    object attributes:{key required : {
     display name: Parameter Name
     type: string
    }    value : {
     display name: Parameter Value
     type: string
    }    }

    readOptions - array[object]

    Options used when reading input from Solr or other sources.

    object attributes:{key required : {
     display name: Parameter Name
     type: string
    }    value : {
     display name: Parameter Value
     type: string
    }    }

    deployModelName - stringrequired

    The model name of the Ray deployment to deploy (must be a valid lowercased DNS subdomain with no underscores).

    <= 30 characters

    Match pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*$

    modelMinReplicas - integer

    Minimum number of replicas of the model to be deployed

    Default: 1

    modelMaxReplicas - integer

    Maximum number of replicas of the model to be deployed

    Default: 1

    modelCpuLimit - numberrequired

    Maximum number of CPUs that can be allocated to a single model replica

    Default: 1

    modelMemoryLimit - stringrequired

    Maximum amount of memory that can be allocated to a single model replica

    Match pattern: ^([+-]?[0-9.]+)([eEinumkKMGTP]*[-+]?[0-9]*)$

    Default: 1Gi

    modelImportPath - string

    The path to your top-level Ray Serve deployment (or the same path passed to `serve run`)

    Default: deployment:app

    modelDockerRepo - stringrequired

    Defines the Docker repository where the model image is located.

    modelDockerImage - stringrequired

    Name of the model's docker image

    modelDockerSecret - string

    Defines the Kubernetes secret to be used with the Docker repository

    type - stringrequired

    Default: argo-deploy-ray-model

    Allowed values: argo-deploy-ray-model