Skip to content

Commit c9f3c14

Browse files
sagemaker-botsagemaker-bot
authored
Daily Sync with Botocore v1.38.27 on 2025/06/02 (#305)
1 parent c557d9e commit c9f3c14

File tree

3 files changed

+221
-0
lines changed

3 files changed

+221
-0
lines changed

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

Lines changed: 93 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -7023,6 +7023,10 @@
70237023
},
70247024
"documentation":"<p>The SageMaker Canvas application settings.</p>"
70257025
},
7026+
"CapacityReservationPreference":{
7027+
"type":"string",
7028+
"enum":["capacity-reservations-only"]
7029+
},
70267030
"CapacitySize":{
70277031
"type":"structure",
70287032
"required":[
@@ -19326,6 +19330,33 @@
1932619330
},
1932719331
"documentation":"<p>A collection of EBS storage settings that apply to both private and shared spaces.</p>"
1932819332
},
19333+
"Ec2CapacityReservation":{
19334+
"type":"structure",
19335+
"members":{
19336+
"Ec2CapacityReservationId":{
19337+
"shape":"Ec2CapacityReservationId",
19338+
"documentation":"<p>The unique identifier for an EC2 capacity reservation that's part of the ML capacity reservation.</p>"
19339+
},
19340+
"TotalInstanceCount":{
19341+
"shape":"TaskCount",
19342+
"documentation":"<p>The number of instances that you allocated to the EC2 capacity reservation.</p>"
19343+
},
19344+
"AvailableInstanceCount":{
19345+
"shape":"TaskCount",
19346+
"documentation":"<p>The number of instances that are currently available in the EC2 capacity reservation.</p>"
19347+
},
19348+
"UsedByCurrentEndpoint":{
19349+
"shape":"TaskCount",
19350+
"documentation":"<p>The number of instances from the EC2 capacity reservation that are being used by the endpoint.</p>"
19351+
}
19352+
},
19353+
"documentation":"<p>The EC2 capacity reservations that are shared to an ML capacity reservation.</p>"
19354+
},
19355+
"Ec2CapacityReservationId":{"type":"string"},
19356+
"Ec2CapacityReservationsList":{
19357+
"type":"list",
19358+
"member":{"shape":"Ec2CapacityReservation"}
19359+
},
1932919360
"Edge":{
1933019361
"type":"structure",
1933119362
"members":{
@@ -29342,6 +29373,12 @@
2934229373
"min":0,
2934329374
"pattern":"1|2"
2934429375
},
29376+
"MlReservationArn":{
29377+
"type":"string",
29378+
"max":258,
29379+
"min":20,
29380+
"pattern":"arn:aws[a-z\\-]*:sagemaker:[a-z0-9\\-]*:[0-9]{12}:ml-reservation/.*"
29381+
},
2934529382
"MlTools":{
2934629383
"type":"string",
2934729384
"enum":[
@@ -34305,6 +34342,10 @@
3430534342
"InferenceAmiVersion":{
3430634343
"shape":"ProductionVariantInferenceAmiVersion",
3430734344
"documentation":"<p>Specifies an option from a collection of preconfigured Amazon Machine Image (AMI) images. Each image is configured by Amazon Web Services with a set of software and driver versions. Amazon Web Services optimizes these configurations for different machine learning workloads.</p> <p>By selecting an AMI version, you can ensure that your inference environment is compatible with specific software requirements, such as CUDA driver versions, Linux kernel versions, or Amazon Web Services Neuron driver versions.</p> <p>The AMI version names, and their configurations, are the following:</p> <dl> <dt>al2-ami-sagemaker-inference-gpu-2</dt> <dd> <ul> <li> <p>Accelerator: GPU</p> </li> <li> <p>NVIDIA driver version: 535</p> </li> <li> <p>CUDA version: 12.2</p> </li> </ul> </dd> <dt>al2-ami-sagemaker-inference-gpu-2-1</dt> <dd> <ul> <li> <p>Accelerator: GPU</p> </li> <li> <p>NVIDIA driver version: 535</p> </li> <li> <p>CUDA version: 12.2</p> </li> <li> <p>NVIDIA Container Toolkit with disabled CUDA-compat mounting</p> </li> </ul> </dd> <dt>al2-ami-sagemaker-inference-gpu-3-1</dt> <dd> <ul> <li> <p>Accelerator: GPU</p> </li> <li> <p>NVIDIA driver version: 550</p> </li> <li> <p>CUDA version: 12.4</p> </li> <li> <p>NVIDIA Container Toolkit with disabled CUDA-compat mounting</p> </li> </ul> </dd> <dt>al2-ami-sagemaker-inference-neuron-2</dt> <dd> <ul> <li> <p>Accelerator: Inferentia2 and Trainium</p> </li> <li> <p>Neuron driver version: 2.19</p> </li> </ul> </dd> </dl>"
34345+
},
34346+
"CapacityReservationConfig":{
34347+
"shape":"ProductionVariantCapacityReservationConfig",
34348+
"documentation":"<p>Settings for the capacity reservation for the compute instances that SageMaker AI reserves for an endpoint. </p>"
3430834349
}
3430934350
},
3431034351
"documentation":"<p> Identifies a model that you want to host and the resources chosen to deploy for hosting it. If you are deploying multiple models, tell SageMaker how to distribute traffic among the models by specifying variant weights. For more information on production variants, check <a href=\"https://docs.aws.amazon.com/sagemaker/latest/dg/model-ab-testing.html\"> Production variants</a>. </p>"
@@ -34320,6 +34361,50 @@
3432034361
"ml.eia2.xlarge"
3432134362
]
3432234363
},
34364+
"ProductionVariantCapacityReservationConfig":{
34365+
"type":"structure",
34366+
"members":{
34367+
"CapacityReservationPreference":{
34368+
"shape":"CapacityReservationPreference",
34369+
"documentation":"<p>Options that you can choose for the capacity reservation. SageMaker AI supports the following options:</p> <dl> <dt>capacity-reservations-only</dt> <dd> <p>SageMaker AI launches instances only into an ML capacity reservation. If no capacity is available, the instances fail to launch.</p> </dd> </dl>"
34370+
},
34371+
"MlReservationArn":{
34372+
"shape":"MlReservationArn",
34373+
"documentation":"<p>The Amazon Resource Name (ARN) that uniquely identifies the ML capacity reservation that SageMaker AI applies when it deploys the endpoint.</p>"
34374+
}
34375+
},
34376+
"documentation":"<p>Settings for the capacity reservation for the compute instances that SageMaker AI reserves for an endpoint. </p>"
34377+
},
34378+
"ProductionVariantCapacityReservationSummary":{
34379+
"type":"structure",
34380+
"members":{
34381+
"MlReservationArn":{
34382+
"shape":"MlReservationArn",
34383+
"documentation":"<p>The Amazon Resource Name (ARN) that uniquely identifies the ML capacity reservation that SageMaker AI applies when it deploys the endpoint.</p>"
34384+
},
34385+
"CapacityReservationPreference":{
34386+
"shape":"CapacityReservationPreference",
34387+
"documentation":"<p>The option that you chose for the capacity reservation. SageMaker AI supports the following options:</p> <dl> <dt>capacity-reservations-only</dt> <dd> <p>SageMaker AI launches instances only into an ML capacity reservation. If no capacity is available, the instances fail to launch.</p> </dd> </dl>"
34388+
},
34389+
"TotalInstanceCount":{
34390+
"shape":"TaskCount",
34391+
"documentation":"<p>The number of instances that you allocated to the ML capacity reservation.</p>"
34392+
},
34393+
"AvailableInstanceCount":{
34394+
"shape":"TaskCount",
34395+
"documentation":"<p>The number of instances that are currently available in the ML capacity reservation.</p>"
34396+
},
34397+
"UsedByCurrentEndpoint":{
34398+
"shape":"TaskCount",
34399+
"documentation":"<p>The number of instances from the ML capacity reservation that are being used by the endpoint.</p>"
34400+
},
34401+
"Ec2CapacityReservations":{
34402+
"shape":"Ec2CapacityReservationsList",
34403+
"documentation":"<p>The EC2 capacity reservations that are shared to this ML capacity reservation, if any.</p>"
34404+
}
34405+
},
34406+
"documentation":"<p>Details about an ML capacity reservation.</p>"
34407+
},
3432334408
"ProductionVariantContainerStartupHealthCheckTimeoutInSeconds":{
3432434409
"type":"integer",
3432534410
"box":true,
@@ -34732,6 +34817,10 @@
3473234817
"RoutingConfig":{
3473334818
"shape":"ProductionVariantRoutingConfig",
3473434819
"documentation":"<p>Settings that control how the endpoint routes incoming traffic to the instances that the endpoint hosts.</p>"
34820+
},
34821+
"CapacityReservationConfig":{
34822+
"shape":"ProductionVariantCapacityReservationSummary",
34823+
"documentation":"<p>Settings for the capacity reservation for the compute instances that SageMaker AI reserves for an endpoint. </p>"
3473534824
}
3473634825
},
3473734826
"documentation":"<p>Describes weight and capacities for a production variant associated with an endpoint. If you sent a request to the <code>UpdateEndpointWeightsAndCapacities</code> API and the endpoint status is <code>Updating</code>, you get different desired and current values. </p>"
@@ -41161,6 +41250,10 @@
4116141250
"ProjectS3Path":{
4116241251
"shape":"S3Uri",
4116341252
"documentation":"<p>The location where Amazon S3 stores temporary execution data and other artifacts for the project that corresponds to the domain.</p>"
41253+
},
41254+
"SingleSignOnApplicationArn":{
41255+
"shape":"SingleSignOnApplicationArn",
41256+
"documentation":"<p>The ARN of the application managed by SageMaker AI and SageMaker Unified Studio in the Amazon Web Services IAM Identity Center.</p>"
4116441257
}
4116541258
},
4116641259
"documentation":"<p>The settings that apply to an Amazon SageMaker AI domain when you use it in Amazon SageMaker Unified Studio.</p>"

‎src/sagemaker_core/main/code_injection/shape_dag.py‎

Lines changed: 63 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -6296,6 +6296,24 @@
62966296
],
62976297
"type": "structure",
62986298
},
6299+
"Ec2CapacityReservation": {
6300+
"members": [
6301+
{
6302+
"name": "Ec2CapacityReservationId",
6303+
"shape": "Ec2CapacityReservationId",
6304+
"type": "string",
6305+
},
6306+
{"name": "TotalInstanceCount", "shape": "TaskCount", "type": "integer"},
6307+
{"name": "AvailableInstanceCount", "shape": "TaskCount", "type": "integer"},
6308+
{"name": "UsedByCurrentEndpoint", "shape": "TaskCount", "type": "integer"},
6309+
],
6310+
"type": "structure",
6311+
},
6312+
"Ec2CapacityReservationsList": {
6313+
"member_shape": "Ec2CapacityReservation",
6314+
"member_type": "structure",
6315+
"type": "list",
6316+
},
62996317
"Edge": {
63006318
"members": [
63016319
{"name": "SourceArn", "shape": "AssociationEntityArn", "type": "string"},
@@ -12393,6 +12411,41 @@
1239312411
"shape": "ProductionVariantInferenceAmiVersion",
1239412412
"type": "string",
1239512413
},
12414+
{
12415+
"name": "CapacityReservationConfig",
12416+
"shape": "ProductionVariantCapacityReservationConfig",
12417+
"type": "structure",
12418+
},
12419+
],
12420+
"type": "structure",
12421+
},
12422+
"ProductionVariantCapacityReservationConfig": {
12423+
"members": [
12424+
{
12425+
"name": "CapacityReservationPreference",
12426+
"shape": "CapacityReservationPreference",
12427+
"type": "string",
12428+
},
12429+
{"name": "MlReservationArn", "shape": "MlReservationArn", "type": "string"},
12430+
],
12431+
"type": "structure",
12432+
},
12433+
"ProductionVariantCapacityReservationSummary": {
12434+
"members": [
12435+
{"name": "MlReservationArn", "shape": "MlReservationArn", "type": "string"},
12436+
{
12437+
"name": "CapacityReservationPreference",
12438+
"shape": "CapacityReservationPreference",
12439+
"type": "string",
12440+
},
12441+
{"name": "TotalInstanceCount", "shape": "TaskCount", "type": "integer"},
12442+
{"name": "AvailableInstanceCount", "shape": "TaskCount", "type": "integer"},
12443+
{"name": "UsedByCurrentEndpoint", "shape": "TaskCount", "type": "integer"},
12444+
{
12445+
"name": "Ec2CapacityReservations",
12446+
"shape": "Ec2CapacityReservationsList",
12447+
"type": "list",
12448+
},
1239612449
],
1239712450
"type": "structure",
1239812451
},
@@ -12493,6 +12546,11 @@
1249312546
"shape": "ProductionVariantRoutingConfig",
1249412547
"type": "structure",
1249512548
},
12549+
{
12550+
"name": "CapacityReservationConfig",
12551+
"shape": "ProductionVariantCapacityReservationSummary",
12552+
"type": "structure",
12553+
},
1249612554
],
1249712555
"type": "structure",
1249812556
},
@@ -14833,6 +14891,11 @@
1483314891
{"name": "ProjectId", "shape": "UnifiedStudioProjectId", "type": "string"},
1483414892
{"name": "EnvironmentId", "shape": "UnifiedStudioEnvironmentId", "type": "string"},
1483514893
{"name": "ProjectS3Path", "shape": "S3Uri", "type": "string"},
14894+
{
14895+
"name": "SingleSignOnApplicationArn",
14896+
"shape": "SingleSignOnApplicationArn",
14897+
"type": "string",
14898+
},
1483614899
],
1483714900
"type": "structure",
1483814901
},

‎src/sagemaker_core/main/shapes.py‎

Lines changed: 65 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -4779,6 +4779,7 @@ class UnifiedStudioSettings(Base):
47794779
project_id: The ID of the Amazon SageMaker Unified Studio project that corresponds to the domain.
47804780
environment_id: The ID of the environment that Amazon SageMaker Unified Studio associates with the domain.
47814781
project_s3_path: The location where Amazon S3 stores temporary execution data and other artifacts for the project that corresponds to the domain.
4782+
single_sign_on_application_arn: The ARN of the application managed by SageMaker AI and SageMaker Unified Studio in the Amazon Web Services IAM Identity Center.
47824783
"""
47834784

47844785
studio_web_portal_access: Optional[str] = Unassigned()
@@ -4788,6 +4789,7 @@ class UnifiedStudioSettings(Base):
47884789
project_id: Optional[str] = Unassigned()
47894790
environment_id: Optional[str] = Unassigned()
47904791
project_s3_path: Optional[str] = Unassigned()
4792+
single_sign_on_application_arn: Optional[str] = Unassigned()
47914793

47924794

47934795
class DomainSettings(Base):
@@ -4966,6 +4968,21 @@ class ProductionVariantRoutingConfig(Base):
49664968
routing_strategy: str
49674969

49684970

4971+
class ProductionVariantCapacityReservationConfig(Base):
4972+
"""
4973+
ProductionVariantCapacityReservationConfig
4974+
Settings for the capacity reservation for the compute instances that SageMaker AI reserves for an endpoint.
4975+
4976+
Attributes
4977+
----------------------
4978+
capacity_reservation_preference: Options that you can choose for the capacity reservation. SageMaker AI supports the following options: capacity-reservations-only SageMaker AI launches instances only into an ML capacity reservation. If no capacity is available, the instances fail to launch.
4979+
ml_reservation_arn: The Amazon Resource Name (ARN) that uniquely identifies the ML capacity reservation that SageMaker AI applies when it deploys the endpoint.
4980+
"""
4981+
4982+
capacity_reservation_preference: Optional[str] = Unassigned()
4983+
ml_reservation_arn: Optional[str] = Unassigned()
4984+
4985+
49694986
class ProductionVariant(Base):
49704987
"""
49714988
ProductionVariant
@@ -4988,6 +5005,7 @@ class ProductionVariant(Base):
49885005
managed_instance_scaling: Settings that control the range in the number of instances that the endpoint provisions as it scales up or down to accommodate traffic.
49895006
routing_config: Settings that control how the endpoint routes incoming traffic to the instances that the endpoint hosts.
49905007
inference_ami_version: Specifies an option from a collection of preconfigured Amazon Machine Image (AMI) images. Each image is configured by Amazon Web Services with a set of software and driver versions. Amazon Web Services optimizes these configurations for different machine learning workloads. By selecting an AMI version, you can ensure that your inference environment is compatible with specific software requirements, such as CUDA driver versions, Linux kernel versions, or Amazon Web Services Neuron driver versions. The AMI version names, and their configurations, are the following: al2-ami-sagemaker-inference-gpu-2 Accelerator: GPU NVIDIA driver version: 535 CUDA version: 12.2 al2-ami-sagemaker-inference-gpu-2-1 Accelerator: GPU NVIDIA driver version: 535 CUDA version: 12.2 NVIDIA Container Toolkit with disabled CUDA-compat mounting al2-ami-sagemaker-inference-gpu-3-1 Accelerator: GPU NVIDIA driver version: 550 CUDA version: 12.4 NVIDIA Container Toolkit with disabled CUDA-compat mounting al2-ami-sagemaker-inference-neuron-2 Accelerator: Inferentia2 and Trainium Neuron driver version: 2.19
5008+
capacity_reservation_config: Settings for the capacity reservation for the compute instances that SageMaker AI reserves for an endpoint.
49915009
"""
49925010

49935011
variant_name: str
@@ -5005,6 +5023,7 @@ class ProductionVariant(Base):
50055023
managed_instance_scaling: Optional[ProductionVariantManagedInstanceScaling] = Unassigned()
50065024
routing_config: Optional[ProductionVariantRoutingConfig] = Unassigned()
50075025
inference_ami_version: Optional[str] = Unassigned()
5026+
capacity_reservation_config: Optional[ProductionVariantCapacityReservationConfig] = Unassigned()
50085027

50095028

50105029
class DataCaptureConfig(Base):
@@ -8164,6 +8183,48 @@ class ProductionVariantStatus(Base):
81648183
start_time: Optional[datetime.datetime] = Unassigned()
81658184

81668185

8186+
class Ec2CapacityReservation(Base):
8187+
"""
8188+
Ec2CapacityReservation
8189+
The EC2 capacity reservations that are shared to an ML capacity reservation.
8190+
8191+
Attributes
8192+
----------------------
8193+
ec2_capacity_reservation_id: The unique identifier for an EC2 capacity reservation that's part of the ML capacity reservation.
8194+
total_instance_count: The number of instances that you allocated to the EC2 capacity reservation.
8195+
available_instance_count: The number of instances that are currently available in the EC2 capacity reservation.
8196+
used_by_current_endpoint: The number of instances from the EC2 capacity reservation that are being used by the endpoint.
8197+
"""
8198+
8199+
ec2_capacity_reservation_id: Optional[str] = Unassigned()
8200+
total_instance_count: Optional[int] = Unassigned()
8201+
available_instance_count: Optional[int] = Unassigned()
8202+
used_by_current_endpoint: Optional[int] = Unassigned()
8203+
8204+
8205+
class ProductionVariantCapacityReservationSummary(Base):
8206+
"""
8207+
ProductionVariantCapacityReservationSummary
8208+
Details about an ML capacity reservation.
8209+
8210+
Attributes
8211+
----------------------
8212+
ml_reservation_arn: The Amazon Resource Name (ARN) that uniquely identifies the ML capacity reservation that SageMaker AI applies when it deploys the endpoint.
8213+
capacity_reservation_preference: The option that you chose for the capacity reservation. SageMaker AI supports the following options: capacity-reservations-only SageMaker AI launches instances only into an ML capacity reservation. If no capacity is available, the instances fail to launch.
8214+
total_instance_count: The number of instances that you allocated to the ML capacity reservation.
8215+
available_instance_count: The number of instances that are currently available in the ML capacity reservation.
8216+
used_by_current_endpoint: The number of instances from the ML capacity reservation that are being used by the endpoint.
8217+
ec2_capacity_reservations: The EC2 capacity reservations that are shared to this ML capacity reservation, if any.
8218+
"""
8219+
8220+
ml_reservation_arn: Optional[str] = Unassigned()
8221+
capacity_reservation_preference: Optional[str] = Unassigned()
8222+
total_instance_count: Optional[int] = Unassigned()
8223+
available_instance_count: Optional[int] = Unassigned()
8224+
used_by_current_endpoint: Optional[int] = Unassigned()
8225+
ec2_capacity_reservations: Optional[List[Ec2CapacityReservation]] = Unassigned()
8226+
8227+
81678228
class ProductionVariantSummary(Base):
81688229
"""
81698230
ProductionVariantSummary
@@ -8182,6 +8243,7 @@ class ProductionVariantSummary(Base):
81828243
desired_serverless_config: The serverless configuration requested for the endpoint update.
81838244
managed_instance_scaling: Settings that control the range in the number of instances that the endpoint provisions as it scales up or down to accommodate traffic.
81848245
routing_config: Settings that control how the endpoint routes incoming traffic to the instances that the endpoint hosts.
8246+
capacity_reservation_config: Settings for the capacity reservation for the compute instances that SageMaker AI reserves for an endpoint.
81858247
"""
81868248

81878249
variant_name: str
@@ -8195,6 +8257,9 @@ class ProductionVariantSummary(Base):
81958257
desired_serverless_config: Optional[ProductionVariantServerlessConfig] = Unassigned()
81968258
managed_instance_scaling: Optional[ProductionVariantManagedInstanceScaling] = Unassigned()
81978259
routing_config: Optional[ProductionVariantRoutingConfig] = Unassigned()
8260+
capacity_reservation_config: Optional[ProductionVariantCapacityReservationSummary] = (
8261+
Unassigned()
8262+
)
81988263

81998264

82008265
class PendingProductionVariantSummary(Base):

0 commit comments

Comments
 (0)