Values_1.InferenceMetricsSourceThe metrics for an existing endpoint compared in an Inference Recommender job.
type nonrec t = {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 invocations per minute for the instance.
*)}val make :
?maxInvocations:Values_0.Integer.t ->
?modelLatency:Values_0.Integer.t ->
unit ->
t