| Package | Description |
|---|---|
| com.amazonaws.services.sagemaker.model |
| Modifier and Type | Method and Description |
|---|---|
InferenceMetrics |
InferenceMetrics.clone() |
InferenceMetrics |
RecommendationJobInferenceBenchmark.getEndpointMetrics() |
InferenceMetrics |
EndpointPerformance.getMetrics()
The metrics for an existing endpoint.
|
InferenceMetrics |
InferenceMetrics.withMaxInvocations(Integer maxInvocations)
The expected maximum number of requests per minute for the instance.
|
InferenceMetrics |
InferenceMetrics.withModelLatency(Integer modelLatency)
The expected model latency at maximum invocations per minute for the instance.
|
| Modifier and Type | Method and Description |
|---|---|
void |
RecommendationJobInferenceBenchmark.setEndpointMetrics(InferenceMetrics endpointMetrics) |
void |
EndpointPerformance.setMetrics(InferenceMetrics metrics)
The metrics for an existing endpoint.
|
RecommendationJobInferenceBenchmark |
RecommendationJobInferenceBenchmark.withEndpointMetrics(InferenceMetrics endpointMetrics) |
EndpointPerformance |
EndpointPerformance.withMetrics(InferenceMetrics metrics)
The metrics for an existing endpoint.
|
Copyright © 2023. All rights reserved.