Skip to content

InferenceMetrics

Source code in docs_src/capo_sagemaker/types/inference_metrics.py 
11
12
13
14
15
class InferenceMetrics(TypedDict, closed=True):
    max_invocations: NotRequired["capo_sagemaker.types.integer.Integer"]
    """<p>The expected maximum number of requests per minute for the instance.</p>"""
    model_latency: NotRequired["capo_sagemaker.types.integer.Integer"]
    """<p>The expected model latency at maximum invocations per minute for the instance.</p>"""

max_invocations instance-attribute 

max_invocations: NotRequired[Integer]

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

model_latency instance-attribute 

model_latency: NotRequired[Integer]

The expected model latency at maximum invocations per minute for the instance.