Skip to content

RecommendationJobStoppingConditions

Used by
Source code in docs_src/capo_sagemaker/types/recommendation_job_stopping_conditions.py 
13
14
15
16
17
18
19
20
21
22
23
class RecommendationJobStoppingConditions(TypedDict, closed=True):
    max_invocations: NotRequired["capo_sagemaker.types.integer.Integer"]
    """<p>The maximum number of requests per minute expected for the endpoint.</p>"""
    model_latency_thresholds: NotRequired[
        "capo_sagemaker.types.model_latency_thresholds.ModelLatencyThresholds"
    ]
    """<p>The interval of time taken by a model to respond as viewed from SageMaker. The interval includes the local communication time taken to send the request and to fetch the response from the container of a model and the time taken to complete the inference in the container.</p>"""
    flat_invocations: NotRequired[
        "capo_sagemaker.types.flat_invocations.FlatInvocations"
    ]
    """<p>Stops a load test when the number of invocations (TPS) peaks and flattens, which means that the instance has reached capacity. The default value is <code>Stop</code>. If you want the load test to continue after invocations have flattened, set the value to <code>Continue</code>.</p>"""

flat_invocations instance-attribute 

flat_invocations: NotRequired[FlatInvocations]

Stops a load test when the number of invocations (TPS) peaks and flattens, which means that the instance has reached capacity. The default value is Stop. If you want the load test to continue after invocations have flattened, set the value to Continue.

max_invocations instance-attribute 

max_invocations: NotRequired[Integer]

The maximum number of requests per minute expected for the endpoint.

model_latency_thresholds instance-attribute 

model_latency_thresholds: NotRequired[ModelLatencyThresholds]

The interval of time taken by a model to respond as viewed from SageMaker. The interval includes the local communication time taken to send the request and to fetch the response from the container of a model and the time taken to complete the inference in the container.