Values_1.RecommendationMetricsSourceThe metrics of recommendations.
type nonrec t = {costPerHour : Values_0.Float_.t option;Defines the cost per hour for the instance.
*)costPerInference : Values_0.Float_.t option;Defines the cost per inference for the instance .
*)maxInvocations : Values_0.Integer.t option;The expected maximum number of requests per minute for the instance.
*)modelLatency : Values_0.Integer.t option;The expected model latency at maximum invocation per minute for the instance.
*)cpuUtilization : UtilizationMetric.t option;The expected CPU utilization at maximum invocations per minute for the instance. NaN indicates that the value is not available.
*)memoryUtilization : UtilizationMetric.t option;The expected memory utilization at maximum invocations per minute for the instance. NaN indicates that the value is not available.
*)modelSetupTime : ModelSetupTime.t option;The time it takes to launch new compute resources for a serverless endpoint. The time can vary depending on the model size, how long it takes to download the model, and the start-up time of the container. NaN indicates that the value is not available.
*)}val to_value :
t ->
[> `Structure of
(string
* [> `Float of Values_0.Float_.t | `Integer of Values_0.Integer.t ])
list ]