Type Alias CreateDeploymentRequest

CreateDeploymentRequest: {
    acceptEula?: boolean;
    endpoints: LLMInference.v1beta1.EndpointSpec[];
    maxSize?: number;
    minSize?: number;
    modelName: string;
    name?: string;
    nodeType: string;
    projectId?: string;
    region?: Region;
    tags?: string[];
}

Type declaration

  • OptionalacceptEula?: boolean

    If the model has an EULA, you must accept it before proceeding. The terms of the EULA can be retrieved using the GetModelEula API call.

  • endpoints: LLMInference.v1beta1.EndpointSpec[]

    List of endpoints to create.

  • OptionalmaxSize?: number

    Defines the maximum size of the pool.

  • OptionalminSize?: number

    Defines the minimum size of the pool.

  • modelName: string

    Name of the model to use.

  • Optionalname?: string

    Name of the deployment.

  • nodeType: string

    Name of the node type to use.

  • OptionalprojectId?: string

    ID of the Project to create the deployment in.

  • Optionalregion?: Region

    Region to target. If none is passed will use default region from the config.

  • Optionaltags?: string[]

    List of tags to apply to the deployment.

Settings