Package Classes (0.1.0)

Summary of entries of Classes for google-cloud-gkerecommender.

Classes

GkeInferenceQuickstartAsyncClient

GKE Inference Quickstart (GIQ) service provides profiles with performance metrics for popular models and model servers across multiple accelerators. These profiles help generate optimized best practices for running inference on GKE.

GkeInferenceQuickstartClient

GKE Inference Quickstart (GIQ) service provides profiles with performance metrics for popular models and model servers across multiple accelerators. These profiles help generate optimized best practices for running inference on GKE.

FetchModelServerVersionsAsyncPager

A pager for iterating through fetch_model_server_versions requests.

This class thinly wraps an initial FetchModelServerVersionsResponse object, and provides an __aiter__ method to iterate through its model_server_versions field.

If there are more pages, the __aiter__ method will make additional FetchModelServerVersions requests and continue to iterate through the model_server_versions field on the corresponding responses.

All the usual FetchModelServerVersionsResponse attributes are available on the pager. If multiple requests are made, only the most recent response is retained, and thus used for attribute lookup.

FetchModelServerVersionsPager

A pager for iterating through fetch_model_server_versions requests.

This class thinly wraps an initial FetchModelServerVersionsResponse object, and provides an __iter__ method to iterate through its model_server_versions field.

If there are more pages, the __iter__ method will make additional FetchModelServerVersions requests and continue to iterate through the model_server_versions field on the corresponding responses.

All the usual FetchModelServerVersionsResponse attributes are available on the pager. If multiple requests are made, only the most recent response is retained, and thus used for attribute lookup.

FetchModelServersAsyncPager

A pager for iterating through fetch_model_servers requests.

This class thinly wraps an initial FetchModelServersResponse object, and provides an __aiter__ method to iterate through its model_servers field.

If there are more pages, the __aiter__ method will make additional FetchModelServers requests and continue to iterate through the model_servers field on the corresponding responses.

All the usual FetchModelServersResponse attributes are available on the pager. If multiple requests are made, only the most recent response is retained, and thus used for attribute lookup.

FetchModelServersPager

A pager for iterating through fetch_model_servers requests.

This class thinly wraps an initial FetchModelServersResponse object, and provides an __iter__ method to iterate through its model_servers field.

If there are more pages, the __iter__ method will make additional FetchModelServers requests and continue to iterate through the model_servers field on the corresponding responses.

All the usual FetchModelServersResponse attributes are available on the pager. If multiple requests are made, only the most recent response is retained, and thus used for attribute lookup.

FetchModelsAsyncPager

A pager for iterating through fetch_models requests.

This class thinly wraps an initial FetchModelsResponse object, and provides an __aiter__ method to iterate through its models field.

If there are more pages, the __aiter__ method will make additional FetchModels requests and continue to iterate through the models field on the corresponding responses.

All the usual FetchModelsResponse attributes are available on the pager. If multiple requests are made, only the most recent response is retained, and thus used for attribute lookup.

FetchModelsPager

A pager for iterating through fetch_models requests.

This class thinly wraps an initial FetchModelsResponse object, and provides an __iter__ method to iterate through its models field.

If there are more pages, the __iter__ method will make additional FetchModels requests and continue to iterate through the models field on the corresponding responses.

All the usual FetchModelsResponse attributes are available on the pager. If multiple requests are made, only the most recent response is retained, and thus used for attribute lookup.

FetchProfilesAsyncPager

A pager for iterating through fetch_profiles requests.

This class thinly wraps an initial FetchProfilesResponse object, and provides an __aiter__ method to iterate through its profile field.

If there are more pages, the __aiter__ method will make additional FetchProfiles requests and continue to iterate through the profile field on the corresponding responses.

All the usual FetchProfilesResponse attributes are available on the pager. If multiple requests are made, only the most recent response is retained, and thus used for attribute lookup.

FetchProfilesPager

A pager for iterating through fetch_profiles requests.

This class thinly wraps an initial FetchProfilesResponse object, and provides an __iter__ method to iterate through its profile field.

If there are more pages, the __iter__ method will make additional FetchProfiles requests and continue to iterate through the profile field on the corresponding responses.

All the usual FetchProfilesResponse attributes are available on the pager. If multiple requests are made, only the most recent response is retained, and thus used for attribute lookup.

Amount

Represents an amount of money in a specific currency.

Cost

Cost for running a model deployment on a given instance type. Currently, only USD currency code is supported.

.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields

FetchBenchmarkingDataRequest

Request message for GkeInferenceQuickstart.FetchBenchmarkingData.

FetchBenchmarkingDataResponse

Response message for GkeInferenceQuickstart.FetchBenchmarkingData.

FetchModelServerVersionsRequest

Request message for GkeInferenceQuickstart.FetchModelServerVersions.

.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields

FetchModelServerVersionsResponse

Response message for GkeInferenceQuickstart.FetchModelServerVersions.

FetchModelServersRequest

Request message for GkeInferenceQuickstart.FetchModelServers.

.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields

FetchModelServersResponse

Response message for GkeInferenceQuickstart.FetchModelServers.

FetchModelsRequest

Request message for GkeInferenceQuickstart.FetchModels.

.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields

FetchModelsResponse

Response message for GkeInferenceQuickstart.FetchModels.

FetchProfilesRequest

Request message for GkeInferenceQuickstart.FetchProfiles.

.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields

FetchProfilesResponse

Response message for GkeInferenceQuickstart.FetchProfiles.

GenerateOptimizedManifestRequest

Request message for GkeInferenceQuickstart.GenerateOptimizedManifest.

GenerateOptimizedManifestResponse

Response message for GkeInferenceQuickstart.GenerateOptimizedManifest.

KubernetesManifest

A Kubernetes manifest.

MillisecondRange

Represents a range of latency values in milliseconds.

ModelServerInfo

Model server information gives. Valid model server info combinations can be found using GkeInferenceQuickstart.FetchProfiles.

PerformanceRange

Performance range for a model deployment.

PerformanceRequirements

Performance requirements for a profile and or model deployment.

.. _oneof: https://proto-plus-python.readthedocs.io/en/stable/fields.html#oneofs-mutually-exclusive-fields

PerformanceStats

Performance statistics for a model deployment.

Profile

A profile containing information about a model deployment.

ResourcesUsed

Resources used by a model deployment.

StorageConfig

Storage configuration for a model deployment.

TokensPerSecondRange

Represents a range of throughput values in tokens per second.

Modules

pagers

API documentation for gkerecommender_v1.services.gke_inference_quickstart.pagers module.