RecommendationMetrics
The metrics of recommendations.
Contents
- CostPerHour
-
Defines the cost per hour for the instance.
Type: Float
Required: Yes
- CostPerInference
-
Defines the cost per inference for the instance .
Type: Float
Required: Yes
- MaxInvocations
-
The expected maximum number of requests per minute for the instance.
Type: Integer
Required: Yes
- ModelLatency
-
The expected model latency at maximum invocation per minute for the instance.
Type: Integer
Required: Yes
- CpuUtilization
-
The expected CPU utilization at maximum invocations per minute for the instance.
NaNindicates that the value is not available.Type: Float
Valid Range: Minimum value of 0.0.
Required: No
- MemoryUtilization
-
The expected memory utilization at maximum invocations per minute for the instance.
NaNindicates that the value is not available.Type: Float
Valid Range: Minimum value of 0.0.
Required: No
- ModelSetupTime
-
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.
NaNindicates that the value is not available.Type: Integer
Valid Range: Minimum value of 0.
Required: No
See Also
For more information about using this API in one of the language-specific AWS SDKs, see the following:
