Skip to content

Commit 146c4a4

Browse files
sagemaker-botsagemaker-bot
authored
Daily Sync with Botocore v1.37.2 on 2025/02/27 (#251)
1 parent 1b85e94 commit 146c4a4

File tree

4 files changed

+192
-12
lines changed

4 files changed

+192
-12
lines changed

‎sample/sagemaker/2017-07-24/service-2.json‎

Lines changed: 78 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -6513,7 +6513,7 @@
65136513
"BatchDeleteClusterNodesErrorList":{
65146514
"type":"list",
65156515
"member":{"shape":"BatchDeleteClusterNodesError"},
6516-
"max":99,
6516+
"max":3000,
65176517
"min":1
65186518
},
65196519
"BatchDeleteClusterNodesRequest":{
@@ -6529,7 +6529,7 @@
65296529
},
65306530
"NodeIds":{
65316531
"shape":"ClusterNodeIds",
6532-
"documentation":"<p>A list of node IDs to be deleted from the specified cluster.</p> <note> <p>For SageMaker HyperPod clusters using the Slurm workload manager, you cannot remove instances that are configured as Slurm controller nodes.</p> </note>"
6532+
"documentation":"<p>A list of node IDs to be deleted from the specified cluster.</p> <note> <ul> <li> <p>For SageMaker HyperPod clusters using the Slurm workload manager, you cannot remove instances that are configured as Slurm controller nodes.</p> </li> <li> <p>If you need to delete more than 99 instances, contact <a href=\"http://aws.amazon.com/contact-us/\">Support</a> for assistance.</p> </li> </ul> </note>"
65336533
}
65346534
}
65356535
},
@@ -7986,7 +7986,7 @@
79867986
"ClusterNodeIds":{
79877987
"type":"list",
79887988
"member":{"shape":"ClusterNodeId"},
7989-
"max":99,
7989+
"max":3000,
79907990
"min":1
79917991
},
79927992
"ClusterNodeRecovery":{
@@ -15959,6 +15959,10 @@
1595915959
"InferenceComponentStatus":{
1596015960
"shape":"InferenceComponentStatus",
1596115961
"documentation":"<p>The status of the inference component.</p>"
15962+
},
15963+
"LastDeploymentConfig":{
15964+
"shape":"InferenceComponentDeploymentConfig",
15965+
"documentation":"<p>The deployment and rollback settings that you assigned to the inference component.</p>"
1596215966
}
1596315967
}
1596415968
},
@@ -19977,7 +19981,7 @@
1997719981
"documentation":"<p>The list of tags that are associated with the experiment. You can use <a href=\"https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_Search.html\">Search</a> API to search on the tags.</p>"
1997819982
}
1997919983
},
19980-
"documentation":"<p>The properties of an experiment as returned by the <a href=\"https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_Search.html\">Search</a> API.</p>"
19984+
"documentation":"<p>The properties of an experiment as returned by the <a href=\"https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_Search.html\">Search</a> API. For information about experiments, see the <a href=\"https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateExperiment.html\">CreateExperiment</a> API.</p>"
1998119985
},
1998219986
"ExperimentArn":{
1998319987
"type":"string",
@@ -22669,6 +22673,31 @@
2266922673
"max":2048,
2267022674
"min":20
2267122675
},
22676+
"InferenceComponentCapacitySize":{
22677+
"type":"structure",
22678+
"required":[
22679+
"Type",
22680+
"Value"
22681+
],
22682+
"members":{
22683+
"Type":{
22684+
"shape":"InferenceComponentCapacitySizeType",
22685+
"documentation":"<p>Specifies the endpoint capacity type.</p> <dl> <dt>COPY_COUNT</dt> <dd> <p>The endpoint activates based on the number of inference component copies.</p> </dd> <dt>CAPACITY_PERCENT</dt> <dd> <p>The endpoint activates based on the specified percentage of capacity.</p> </dd> </dl>"
22686+
},
22687+
"Value":{
22688+
"shape":"CapacitySizeValue",
22689+
"documentation":"<p>Defines the capacity size, either as a number of inference component copies or a capacity percentage.</p>"
22690+
}
22691+
},
22692+
"documentation":"<p>Specifies the type and size of the endpoint capacity to activate for a rolling deployment or a rollback strategy. You can specify your batches as either of the following:</p> <ul> <li> <p>A count of inference component copies </p> </li> <li> <p>The overall percentage or your fleet </p> </li> </ul> <p>For a rollback strategy, if you don't specify the fields in this object, or if you set the <code>Value</code> parameter to 100%, then SageMaker AI uses a blue/green rollback strategy and rolls all traffic back to the blue fleet.</p>"
22693+
},
22694+
"InferenceComponentCapacitySizeType":{
22695+
"type":"string",
22696+
"enum":[
22697+
"COPY_COUNT",
22698+
"CAPACITY_PERCENT"
22699+
]
22700+
},
2267222701
"InferenceComponentComputeResourceRequirements":{
2267322702
"type":"structure",
2267422703
"required":["MinMemoryRequiredInMb"],
@@ -22729,6 +22758,18 @@
2272922758
"type":"integer",
2273022759
"min":0
2273122760
},
22761+
"InferenceComponentDeploymentConfig":{
22762+
"type":"structure",
22763+
"required":["RollingUpdatePolicy"],
22764+
"members":{
22765+
"RollingUpdatePolicy":{
22766+
"shape":"InferenceComponentRollingUpdatePolicy",
22767+
"documentation":"<p>Specifies a rolling deployment strategy for updating a SageMaker AI endpoint.</p>"
22768+
},
22769+
"AutoRollbackConfiguration":{"shape":"AutoRollbackConfig"}
22770+
},
22771+
"documentation":"<p>The deployment configuration for an endpoint that hosts inference components. The configuration includes the desired deployment strategy and rollback settings.</p>"
22772+
},
2273222773
"InferenceComponentName":{
2273322774
"type":"string",
2273422775
"max":63,
@@ -22739,6 +22780,32 @@
2273922780
"max":63,
2274022781
"pattern":"[a-zA-Z0-9-]+"
2274122782
},
22783+
"InferenceComponentRollingUpdatePolicy":{
22784+
"type":"structure",
22785+
"required":[
22786+
"MaximumBatchSize",
22787+
"WaitIntervalInSeconds"
22788+
],
22789+
"members":{
22790+
"MaximumBatchSize":{
22791+
"shape":"InferenceComponentCapacitySize",
22792+
"documentation":"<p>The batch size for each rolling step in the deployment process. For each step, SageMaker AI provisions capacity on the new endpoint fleet, routes traffic to that fleet, and terminates capacity on the old endpoint fleet. The value must be between 5% to 50% of the copy count of the inference component.</p>"
22793+
},
22794+
"WaitIntervalInSeconds":{
22795+
"shape":"WaitIntervalInSeconds",
22796+
"documentation":"<p>The length of the baking period, during which SageMaker AI monitors alarms for each batch on the new fleet.</p>"
22797+
},
22798+
"MaximumExecutionTimeoutInSeconds":{
22799+
"shape":"MaximumExecutionTimeoutInSeconds",
22800+
"documentation":"<p>The time limit for the total deployment. Exceeding this limit causes a timeout.</p>"
22801+
},
22802+
"RollbackMaximumBatchSize":{
22803+
"shape":"InferenceComponentCapacitySize",
22804+
"documentation":"<p>The batch size for a rollback to the old endpoint fleet. If this field is absent, the value is set to the default, which is 100% of the total capacity. When the default is used, SageMaker AI provisions the entire capacity of the old fleet at once during rollback.</p>"
22805+
}
22806+
},
22807+
"documentation":"<p>Specifies a rolling deployment strategy for updating a SageMaker AI inference component.</p>"
22808+
},
2274222809
"InferenceComponentRuntimeConfig":{
2274322810
"type":"structure",
2274422811
"required":["CopyCount"],
@@ -29780,7 +29847,7 @@
2978029847
"members":{
2978129848
"ModelPackageName":{
2978229849
"shape":"EntityName",
29783-
"documentation":"<p>The name of the model.</p>"
29850+
"documentation":"<p>The name of the model package. The name can be as follows:</p> <ul> <li> <p>For a versioned model, the name is automatically generated by SageMaker Model Registry and follows the format '<code>ModelPackageGroupName/ModelPackageVersion</code>'.</p> </li> <li> <p>For an unversioned model, you must provide the name.</p> </li> </ul>"
2978429851
},
2978529852
"ModelPackageGroupName":{
2978629853
"shape":"EntityName",
@@ -29897,7 +29964,7 @@
2989729964
"documentation":"<p>Indicates if you want to skip model validation.</p>"
2989829965
}
2989929966
},
29900-
"documentation":"<p>A versioned model that can be deployed for SageMaker inference.</p>"
29967+
"documentation":"<p>A container for your trained model that can be deployed for SageMaker inference. This can include inference code, artifacts, and metadata. The model package type can be one of the following.</p> <ul> <li> <p>Versioned model: A part of a model package group in Model Registry.</p> </li> <li> <p>Unversioned model: Not part of a model package group and used in Amazon Web Services Marketplace.</p> </li> </ul> <p>For more information, see <a href=\"https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateModelPackage.html\"> <code>CreateModelPackage</code> </a>.</p>"
2990129968
},
2990229969
"ModelPackageArn":{
2990329970
"type":"string",
@@ -30011,7 +30078,7 @@
3001130078
"documentation":"<p>A list of the tags associated with the model group. For more information, see <a href=\"https://docs.aws.amazon.com/general/latest/gr/aws_tagging.html\">Tagging Amazon Web Services resources</a> in the <i>Amazon Web Services General Reference Guide</i>.</p>"
3001230079
}
3001330080
},
30014-
"documentation":"<p>A group of versioned models in the model registry.</p>"
30081+
"documentation":"<p>A group of versioned models in the Model Registry.</p>"
3001530082
},
3001630083
"ModelPackageGroupArn":{
3001730084
"type":"string",
@@ -40889,6 +40956,10 @@
4088940956
"RuntimeConfig":{
4089040957
"shape":"InferenceComponentRuntimeConfig",
4089140958
"documentation":"<p>Runtime settings for a model that is deployed with an inference component.</p>"
40959+
},
40960+
"DeploymentConfig":{
40961+
"shape":"InferenceComponentDeploymentConfig",
40962+
"documentation":"<p>The deployment configuration for the inference component. The configuration contains the desired deployment strategy and rollback settings.</p>"
4089240963
}
4089340964
}
4089440965
},

‎src/sagemaker_core/main/code_injection/shape_dag.py‎

Lines changed: 53 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -4911,6 +4911,11 @@
49114911
"shape": "InferenceComponentStatus",
49124912
"type": "string",
49134913
},
4914+
{
4915+
"name": "LastDeploymentConfig",
4916+
"shape": "InferenceComponentDeploymentConfig",
4917+
"type": "structure",
4918+
},
49144919
],
49154920
"type": "structure",
49164921
},
@@ -7670,6 +7675,13 @@
76707675
],
76717676
"type": "structure",
76727677
},
7678+
"InferenceComponentCapacitySize": {
7679+
"members": [
7680+
{"name": "Type", "shape": "InferenceComponentCapacitySizeType", "type": "string"},
7681+
{"name": "Value", "shape": "CapacitySizeValue", "type": "integer"},
7682+
],
7683+
"type": "structure",
7684+
},
76737685
"InferenceComponentComputeResourceRequirements": {
76747686
"members": [
76757687
{"name": "NumberOfCpuCoresRequired", "shape": "NumberOfCpuCores", "type": "float"},
@@ -7699,6 +7711,42 @@
76997711
],
77007712
"type": "structure",
77017713
},
7714+
"InferenceComponentDeploymentConfig": {
7715+
"members": [
7716+
{
7717+
"name": "RollingUpdatePolicy",
7718+
"shape": "InferenceComponentRollingUpdatePolicy",
7719+
"type": "structure",
7720+
},
7721+
{
7722+
"name": "AutoRollbackConfiguration",
7723+
"shape": "AutoRollbackConfig",
7724+
"type": "structure",
7725+
},
7726+
],
7727+
"type": "structure",
7728+
},
7729+
"InferenceComponentRollingUpdatePolicy": {
7730+
"members": [
7731+
{
7732+
"name": "MaximumBatchSize",
7733+
"shape": "InferenceComponentCapacitySize",
7734+
"type": "structure",
7735+
},
7736+
{"name": "WaitIntervalInSeconds", "shape": "WaitIntervalInSeconds", "type": "integer"},
7737+
{
7738+
"name": "MaximumExecutionTimeoutInSeconds",
7739+
"shape": "MaximumExecutionTimeoutInSeconds",
7740+
"type": "integer",
7741+
},
7742+
{
7743+
"name": "RollbackMaximumBatchSize",
7744+
"shape": "InferenceComponentCapacitySize",
7745+
"type": "structure",
7746+
},
7747+
],
7748+
"type": "structure",
7749+
},
77027750
"InferenceComponentRuntimeConfig": {
77037751
"members": [
77047752
{"name": "CopyCount", "shape": "InferenceComponentCopyCount", "type": "integer"}
@@ -15004,6 +15052,11 @@
1500415052
"shape": "InferenceComponentRuntimeConfig",
1500515053
"type": "structure",
1500615054
},
15055+
{
15056+
"name": "DeploymentConfig",
15057+
"shape": "InferenceComponentDeploymentConfig",
15058+
"type": "structure",
15059+
},
1500715060
],
1500815061
"type": "structure",
1500915062
},

‎src/sagemaker_core/main/resources.py‎

Lines changed: 8 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -3874,7 +3874,7 @@ def batch_delete_nodes(
38743874
Deletes specific nodes within a SageMaker HyperPod cluster.
38753875

38763876
Parameters:
3877-
node_ids: A list of node IDs to be deleted from the specified cluster. For SageMaker HyperPod clusters using the Slurm workload manager, you cannot remove instances that are configured as Slurm controller nodes.
3877+
node_ids: A list of node IDs to be deleted from the specified cluster. For SageMaker HyperPod clusters using the Slurm workload manager, you cannot remove instances that are configured as Slurm controller nodes. If you need to delete more than 99 instances, contact Support for assistance.
38783878
session: Boto3 session.
38793879
region: Region name.
38803880

@@ -14801,6 +14801,7 @@ class InferenceComponent(Base):
1480114801
specification: Details about the resources that are deployed with this inference component.
1480214802
runtime_config: Details about the runtime settings for the model that is deployed with the inference component.
1480314803
inference_component_status: The status of the inference component.
14804+
last_deployment_config: The deployment and rollback settings that you assigned to the inference component.
1480414805

1480514806
"""
1480614807

@@ -14815,6 +14816,7 @@ class InferenceComponent(Base):
1481514816
creation_time: Optional[datetime.datetime] = Unassigned()
1481614817
last_modified_time: Optional[datetime.datetime] = Unassigned()
1481714818
inference_component_status: Optional[str] = Unassigned()
14819+
last_deployment_config: Optional[InferenceComponentDeploymentConfig] = Unassigned()
1481814820

1481914821
def get_name(self) -> str:
1482014822
attributes = vars(self)
@@ -14999,10 +15001,14 @@ def update(
1499915001
self,
1500015002
specification: Optional[InferenceComponentSpecification] = Unassigned(),
1500115003
runtime_config: Optional[InferenceComponentRuntimeConfig] = Unassigned(),
15004+
deployment_config: Optional[InferenceComponentDeploymentConfig] = Unassigned(),
1500215005
) -> Optional["InferenceComponent"]:
1500315006
"""
1500415007
Update a InferenceComponent resource
1500515008

15009+
Parameters:
15010+
deployment_config: The deployment configuration for the inference component. The configuration contains the desired deployment strategy and rollback settings.
15011+
1500615012
Returns:
1500715013
The InferenceComponent resource.
1500815014

@@ -15026,6 +15032,7 @@ def update(
1502615032
"InferenceComponentName": self.inference_component_name,
1502715033
"Specification": specification,
1502815034
"RuntimeConfig": runtime_config,
15035+
"DeploymentConfig": deployment_config,
1502915036
}
1503015037
logger.debug(f"Input request: {operation_input_args}")
1503115038
# serialize the input request

‎src/sagemaker_core/main/shapes.py‎

Lines changed: 53 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -8404,6 +8404,55 @@ class InferenceComponentRuntimeConfigSummary(Base):
84048404
current_copy_count: Optional[int] = Unassigned()
84058405

84068406

8407+
class InferenceComponentCapacitySize(Base):
8408+
"""
8409+
InferenceComponentCapacitySize
8410+
Specifies the type and size of the endpoint capacity to activate for a rolling deployment or a rollback strategy. You can specify your batches as either of the following: A count of inference component copies The overall percentage or your fleet For a rollback strategy, if you don't specify the fields in this object, or if you set the Value parameter to 100%, then SageMaker AI uses a blue/green rollback strategy and rolls all traffic back to the blue fleet.
8411+
8412+
Attributes
8413+
----------------------
8414+
type: Specifies the endpoint capacity type. COPY_COUNT The endpoint activates based on the number of inference component copies. CAPACITY_PERCENT The endpoint activates based on the specified percentage of capacity.
8415+
value: Defines the capacity size, either as a number of inference component copies or a capacity percentage.
8416+
"""
8417+
8418+
type: str
8419+
value: int
8420+
8421+
8422+
class InferenceComponentRollingUpdatePolicy(Base):
8423+
"""
8424+
InferenceComponentRollingUpdatePolicy
8425+
Specifies a rolling deployment strategy for updating a SageMaker AI inference component.
8426+
8427+
Attributes
8428+
----------------------
8429+
maximum_batch_size: The batch size for each rolling step in the deployment process. For each step, SageMaker AI provisions capacity on the new endpoint fleet, routes traffic to that fleet, and terminates capacity on the old endpoint fleet. The value must be between 5% to 50% of the copy count of the inference component.
8430+
wait_interval_in_seconds: The length of the baking period, during which SageMaker AI monitors alarms for each batch on the new fleet.
8431+
maximum_execution_timeout_in_seconds: The time limit for the total deployment. Exceeding this limit causes a timeout.
8432+
rollback_maximum_batch_size: The batch size for a rollback to the old endpoint fleet. If this field is absent, the value is set to the default, which is 100% of the total capacity. When the default is used, SageMaker AI provisions the entire capacity of the old fleet at once during rollback.
8433+
"""
8434+
8435+
maximum_batch_size: InferenceComponentCapacitySize
8436+
wait_interval_in_seconds: int
8437+
maximum_execution_timeout_in_seconds: Optional[int] = Unassigned()
8438+
rollback_maximum_batch_size: Optional[InferenceComponentCapacitySize] = Unassigned()
8439+
8440+
8441+
class InferenceComponentDeploymentConfig(Base):
8442+
"""
8443+
InferenceComponentDeploymentConfig
8444+
The deployment configuration for an endpoint that hosts inference components. The configuration includes the desired deployment strategy and rollback settings.
8445+
8446+
Attributes
8447+
----------------------
8448+
rolling_update_policy: Specifies a rolling deployment strategy for updating a SageMaker AI endpoint.
8449+
auto_rollback_configuration
8450+
"""
8451+
8452+
rolling_update_policy: InferenceComponentRollingUpdatePolicy
8453+
auto_rollback_configuration: Optional[AutoRollbackConfig] = Unassigned()
8454+
8455+
84078456
class EndpointMetadata(Base):
84088457
"""
84098458
EndpointMetadata
@@ -9638,7 +9687,7 @@ class EndpointSummary(Base):
96389687
class Experiment(Base):
96399688
"""
96409689
Experiment
9641-
The properties of an experiment as returned by the Search API.
9690+
The properties of an experiment as returned by the Search API. For information about experiments, see the CreateExperiment API.
96429691

96439692
Attributes
96449693
----------------------
@@ -11690,11 +11739,11 @@ class ModelDashboardModel(Base):
1169011739
class ModelPackage(Base):
1169111740
"""
1169211741
ModelPackage
11693-
A versioned model that can be deployed for SageMaker inference.
11742+
A container for your trained model that can be deployed for SageMaker inference. This can include inference code, artifacts, and metadata. The model package type can be one of the following. Versioned model: A part of a model package group in Model Registry. Unversioned model: Not part of a model package group and used in Amazon Web Services Marketplace. For more information, see CreateModelPackage .
1169411743

1169511744
Attributes
1169611745
----------------------
11697-
model_package_name: The name of the model.
11746+
model_package_name: The name of the model package. The name can be as follows: For a versioned model, the name is automatically generated by SageMaker Model Registry and follows the format 'ModelPackageGroupName/ModelPackageVersion'. For an unversioned model, you must provide the name.
1169811747
model_package_group_name: The model group to which the model belongs.
1169911748
model_package_version: The version number of a versioned model.
1170011749
model_package_arn: The Amazon Resource Name (ARN) of the model package.
@@ -11765,7 +11814,7 @@ class ModelPackage(Base):
1176511814
class ModelPackageGroup(Base):
1176611815
"""
1176711816
ModelPackageGroup
11768-
A group of versioned models in the model registry.
11817+
A group of versioned models in the Model Registry.
1176911818

1177011819
Attributes
1177111820
----------------------

0 commit comments

Comments
 (0)