Interface GenerateOptimizedManifestRequestOrBuilder (0.1.0)

public interface GenerateOptimizedManifestRequestOrBuilder extends MessageOrBuilder

Implements

MessageOrBuilder

Methods

getAcceleratorType()

public abstract String getAcceleratorType()

Required. The accelerator type. Use GkeInferenceQuickstart.FetchProfiles to find valid accelerators for a given model_server_info.

string accelerator_type = 2 [(.google.api.field_behavior) = REQUIRED];

Returns
Type	Description
String	The acceleratorType.

getAcceleratorTypeBytes()

public abstract ByteString getAcceleratorTypeBytes()

Required. The accelerator type. Use GkeInferenceQuickstart.FetchProfiles to find valid accelerators for a given model_server_info.

string accelerator_type = 2 [(.google.api.field_behavior) = REQUIRED];

Returns
Type	Description
ByteString	The bytes for acceleratorType.

getKubernetesNamespace()

public abstract String getKubernetesNamespace()

Optional. The kubernetes namespace to deploy the manifests in.

string kubernetes_namespace = 3 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type	Description
String	The kubernetesNamespace.

getKubernetesNamespaceBytes()

public abstract ByteString getKubernetesNamespaceBytes()

Optional. The kubernetes namespace to deploy the manifests in.

string kubernetes_namespace = 3 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type	Description
ByteString	The bytes for kubernetesNamespace.

getModelServerInfo()

public abstract ModelServerInfo getModelServerInfo()

Required. The model server configuration to generate the manifest for. Use GkeInferenceQuickstart.FetchProfiles to find valid configurations.

.google.cloud.gkerecommender.v1.ModelServerInfo model_server_info = 1 [(.google.api.field_behavior) = REQUIRED];

Returns
Type	Description
ModelServerInfo	The modelServerInfo.

getModelServerInfoOrBuilder()

public abstract ModelServerInfoOrBuilder getModelServerInfoOrBuilder()

Required. The model server configuration to generate the manifest for. Use GkeInferenceQuickstart.FetchProfiles to find valid configurations.

.google.cloud.gkerecommender.v1.ModelServerInfo model_server_info = 1 [(.google.api.field_behavior) = REQUIRED];

Returns
Type	Description
ModelServerInfoOrBuilder

getPerformanceRequirements()

public abstract PerformanceRequirements getPerformanceRequirements()

Optional. The performance requirements to use for generating Horizontal Pod Autoscaler (HPA) resources. If provided, the manifest includes HPA resources to adjust the model server replica count to maintain the specified targets (e.g., NTPOT, TTFT) at a P50 latency. Cost targets are not currently supported for HPA generation. If the specified targets are not achievable, the HPA manifest will not be generated.

.google.cloud.gkerecommender.v1.PerformanceRequirements performance_requirements = 4 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type	Description
PerformanceRequirements	The performanceRequirements.

getPerformanceRequirementsOrBuilder()

public abstract PerformanceRequirementsOrBuilder getPerformanceRequirementsOrBuilder()

Optional. The performance requirements to use for generating Horizontal Pod Autoscaler (HPA) resources. If provided, the manifest includes HPA resources to adjust the model server replica count to maintain the specified targets (e.g., NTPOT, TTFT) at a P50 latency. Cost targets are not currently supported for HPA generation. If the specified targets are not achievable, the HPA manifest will not be generated.

.google.cloud.gkerecommender.v1.PerformanceRequirements performance_requirements = 4 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type	Description
PerformanceRequirementsOrBuilder

getStorageConfig()

public abstract StorageConfig getStorageConfig()

Optional. The storage configuration for the model. If not provided, the model is loaded from Huggingface.

.google.cloud.gkerecommender.v1.StorageConfig storage_config = 5 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type	Description
StorageConfig	The storageConfig.

getStorageConfigOrBuilder()

public abstract StorageConfigOrBuilder getStorageConfigOrBuilder()

Optional. The storage configuration for the model. If not provided, the model is loaded from Huggingface.

.google.cloud.gkerecommender.v1.StorageConfig storage_config = 5 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type	Description
StorageConfigOrBuilder

hasModelServerInfo()

public abstract boolean hasModelServerInfo()

Required. The model server configuration to generate the manifest for. Use GkeInferenceQuickstart.FetchProfiles to find valid configurations.

.google.cloud.gkerecommender.v1.ModelServerInfo model_server_info = 1 [(.google.api.field_behavior) = REQUIRED];

Returns
Type	Description
boolean	Whether the modelServerInfo field is set.

hasPerformanceRequirements()

public abstract boolean hasPerformanceRequirements()

Optional. The performance requirements to use for generating Horizontal Pod Autoscaler (HPA) resources. If provided, the manifest includes HPA resources to adjust the model server replica count to maintain the specified targets (e.g., NTPOT, TTFT) at a P50 latency. Cost targets are not currently supported for HPA generation. If the specified targets are not achievable, the HPA manifest will not be generated.

.google.cloud.gkerecommender.v1.PerformanceRequirements performance_requirements = 4 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type	Description
boolean	Whether the performanceRequirements field is set.

hasStorageConfig()

public abstract boolean hasStorageConfig()

Optional. The storage configuration for the model. If not provided, the model is loaded from Huggingface.

.google.cloud.gkerecommender.v1.StorageConfig storage_config = 5 [(.google.api.field_behavior) = OPTIONAL];

Returns
Type	Description
boolean	Whether the storageConfig field is set.