aws-sdk-sagemaker 1.193.0 → 1.194.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: e8563212194efe3f885db18ded340750c68719059405c10110a98fe0a254de83
-  data.tar.gz: 8c32b946394f67fac58c560a9a048ec39d56ab2ea1f1416484de48dbeb99947c
+  metadata.gz: 60973ee75145a047cd16273b84e2c90c71e5f4f79410ca18abc405d322530142
+  data.tar.gz: c3b8a0d376ecde588856d2902f2260fda4df5ee686004457f25edccff047fab3
 SHA512:
-  metadata.gz: 1632e061172d86fd8998029d2b91c397c527dc6329297cacff63dd191a7b81e349ad4ba938c85a178d7056a47b4bbe084f7adc327087dc8c652d87effcc75be5
-  data.tar.gz: 6e7c6e026568146cea2404421c7ce6028e509a6d042af8c25ede1c4e5b141f0b89303e1c4d801d7405338204ea4f27d75c1f7670de963cb6593951988c110559
+  metadata.gz: ab144375ebe73e9a8ba1db86cfc76be055d4a904277d6f8fc474dd1cbc846980c66ab87b90d6892a99798c55fe84197a03c5911bac12295b441c130e7ee12e1c
+  data.tar.gz: 76a347049d001562cda69eb23edab0abe7a60de6f84ecdb31b4aa237ef850122be6210bcf87927af77fcbb2e492d06dd95ebd795a1350113a007ca5cae7e60b4

data/CHANGELOG.md

@@ -1,6 +1,11 @@
 Unreleased Changes
 ------------------
 
+1.194.0 (2023-07-03)
+------------------
+
+* Feature - SageMaker Inference Recommender now accepts new fields SupportedEndpointType and ServerlessConfiguration to support serverless endpoints.
+
 1.193.0 (2023-06-30)
 ------------------
 

data/VERSION

@@ -1 +1 @@
-1.193.0
+1.194.0

data/lib/aws-sdk-sagemaker/client.rb

@@ -4459,7 +4459,7 @@ module Aws::SageMaker
     #       },
     #       endpoint_configurations: [
     #         {
-    #           instance_type: "ml.t2.medium", # required, accepts ml.t2.medium, ml.t2.large, ml.t2.xlarge, ml.t2.2xlarge, ml.m4.xlarge, ml.m4.2xlarge, ml.m4.4xlarge, ml.m4.10xlarge, ml.m4.16xlarge, ml.m5.large, ml.m5.xlarge, ml.m5.2xlarge, ml.m5.4xlarge, ml.m5.12xlarge, ml.m5.24xlarge, ml.m5d.large, ml.m5d.xlarge, ml.m5d.2xlarge, ml.m5d.4xlarge, ml.m5d.12xlarge, ml.m5d.24xlarge, ml.c4.large, ml.c4.xlarge, ml.c4.2xlarge, ml.c4.4xlarge, ml.c4.8xlarge, ml.p2.xlarge, ml.p2.8xlarge, ml.p2.16xlarge, ml.p3.2xlarge, ml.p3.8xlarge, ml.p3.16xlarge, ml.c5.large, ml.c5.xlarge, ml.c5.2xlarge, ml.c5.4xlarge, ml.c5.9xlarge, ml.c5.18xlarge, ml.c5d.large, ml.c5d.xlarge, ml.c5d.2xlarge, ml.c5d.4xlarge, ml.c5d.9xlarge, ml.c5d.18xlarge, ml.g4dn.xlarge, ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g4dn.12xlarge, ml.g4dn.16xlarge, ml.r5.large, ml.r5.xlarge, ml.r5.2xlarge, ml.r5.4xlarge, ml.r5.12xlarge, ml.r5.24xlarge, ml.r5d.large, ml.r5d.xlarge, ml.r5d.2xlarge, ml.r5d.4xlarge, ml.r5d.12xlarge, ml.r5d.24xlarge, ml.inf1.xlarge, ml.inf1.2xlarge, ml.inf1.6xlarge, ml.inf1.24xlarge, ml.c6i.large, ml.c6i.xlarge, ml.c6i.2xlarge, ml.c6i.4xlarge, ml.c6i.8xlarge, ml.c6i.12xlarge, ml.c6i.16xlarge, ml.c6i.24xlarge, ml.c6i.32xlarge, ml.g5.xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.12xlarge, ml.g5.16xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.p4d.24xlarge, ml.c7g.large, ml.c7g.xlarge, ml.c7g.2xlarge, ml.c7g.4xlarge, ml.c7g.8xlarge, ml.c7g.12xlarge, ml.c7g.16xlarge, ml.m6g.large, ml.m6g.xlarge, ml.m6g.2xlarge, ml.m6g.4xlarge, ml.m6g.8xlarge, ml.m6g.12xlarge, ml.m6g.16xlarge, ml.m6gd.large, ml.m6gd.xlarge, ml.m6gd.2xlarge, ml.m6gd.4xlarge, ml.m6gd.8xlarge, ml.m6gd.12xlarge, ml.m6gd.16xlarge, ml.c6g.large, ml.c6g.xlarge, ml.c6g.2xlarge, ml.c6g.4xlarge, ml.c6g.8xlarge, ml.c6g.12xlarge, ml.c6g.16xlarge, ml.c6gd.large, ml.c6gd.xlarge, ml.c6gd.2xlarge, ml.c6gd.4xlarge, ml.c6gd.8xlarge, ml.c6gd.12xlarge, ml.c6gd.16xlarge, ml.c6gn.large, ml.c6gn.xlarge, ml.c6gn.2xlarge, ml.c6gn.4xlarge, ml.c6gn.8xlarge, ml.c6gn.12xlarge, ml.c6gn.16xlarge, ml.r6g.large, ml.r6g.xlarge, ml.r6g.2xlarge, ml.r6g.4xlarge, ml.r6g.8xlarge, ml.r6g.12xlarge, ml.r6g.16xlarge, ml.r6gd.large, ml.r6gd.xlarge, ml.r6gd.2xlarge, ml.r6gd.4xlarge, ml.r6gd.8xlarge, ml.r6gd.12xlarge, ml.r6gd.16xlarge, ml.p4de.24xlarge, ml.trn1.2xlarge, ml.trn1.32xlarge, ml.inf2.xlarge, ml.inf2.8xlarge, ml.inf2.24xlarge, ml.inf2.48xlarge
+    #           instance_type: "ml.t2.medium", # accepts ml.t2.medium, ml.t2.large, ml.t2.xlarge, ml.t2.2xlarge, ml.m4.xlarge, ml.m4.2xlarge, ml.m4.4xlarge, ml.m4.10xlarge, ml.m4.16xlarge, ml.m5.large, ml.m5.xlarge, ml.m5.2xlarge, ml.m5.4xlarge, ml.m5.12xlarge, ml.m5.24xlarge, ml.m5d.large, ml.m5d.xlarge, ml.m5d.2xlarge, ml.m5d.4xlarge, ml.m5d.12xlarge, ml.m5d.24xlarge, ml.c4.large, ml.c4.xlarge, ml.c4.2xlarge, ml.c4.4xlarge, ml.c4.8xlarge, ml.p2.xlarge, ml.p2.8xlarge, ml.p2.16xlarge, ml.p3.2xlarge, ml.p3.8xlarge, ml.p3.16xlarge, ml.c5.large, ml.c5.xlarge, ml.c5.2xlarge, ml.c5.4xlarge, ml.c5.9xlarge, ml.c5.18xlarge, ml.c5d.large, ml.c5d.xlarge, ml.c5d.2xlarge, ml.c5d.4xlarge, ml.c5d.9xlarge, ml.c5d.18xlarge, ml.g4dn.xlarge, ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g4dn.12xlarge, ml.g4dn.16xlarge, ml.r5.large, ml.r5.xlarge, ml.r5.2xlarge, ml.r5.4xlarge, ml.r5.12xlarge, ml.r5.24xlarge, ml.r5d.large, ml.r5d.xlarge, ml.r5d.2xlarge, ml.r5d.4xlarge, ml.r5d.12xlarge, ml.r5d.24xlarge, ml.inf1.xlarge, ml.inf1.2xlarge, ml.inf1.6xlarge, ml.inf1.24xlarge, ml.c6i.large, ml.c6i.xlarge, ml.c6i.2xlarge, ml.c6i.4xlarge, ml.c6i.8xlarge, ml.c6i.12xlarge, ml.c6i.16xlarge, ml.c6i.24xlarge, ml.c6i.32xlarge, ml.g5.xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.12xlarge, ml.g5.16xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.p4d.24xlarge, ml.c7g.large, ml.c7g.xlarge, ml.c7g.2xlarge, ml.c7g.4xlarge, ml.c7g.8xlarge, ml.c7g.12xlarge, ml.c7g.16xlarge, ml.m6g.large, ml.m6g.xlarge, ml.m6g.2xlarge, ml.m6g.4xlarge, ml.m6g.8xlarge, ml.m6g.12xlarge, ml.m6g.16xlarge, ml.m6gd.large, ml.m6gd.xlarge, ml.m6gd.2xlarge, ml.m6gd.4xlarge, ml.m6gd.8xlarge, ml.m6gd.12xlarge, ml.m6gd.16xlarge, ml.c6g.large, ml.c6g.xlarge, ml.c6g.2xlarge, ml.c6g.4xlarge, ml.c6g.8xlarge, ml.c6g.12xlarge, ml.c6g.16xlarge, ml.c6gd.large, ml.c6gd.xlarge, ml.c6gd.2xlarge, ml.c6gd.4xlarge, ml.c6gd.8xlarge, ml.c6gd.12xlarge, ml.c6gd.16xlarge, ml.c6gn.large, ml.c6gn.xlarge, ml.c6gn.2xlarge, ml.c6gn.4xlarge, ml.c6gn.8xlarge, ml.c6gn.12xlarge, ml.c6gn.16xlarge, ml.r6g.large, ml.r6g.xlarge, ml.r6g.2xlarge, ml.r6g.4xlarge, ml.r6g.8xlarge, ml.r6g.12xlarge, ml.r6g.16xlarge, ml.r6gd.large, ml.r6gd.xlarge, ml.r6gd.2xlarge, ml.r6gd.4xlarge, ml.r6gd.8xlarge, ml.r6gd.12xlarge, ml.r6gd.16xlarge, ml.p4de.24xlarge, ml.trn1.2xlarge, ml.trn1.32xlarge, ml.inf2.xlarge, ml.inf2.8xlarge, ml.inf2.24xlarge, ml.inf2.48xlarge
     #           inference_specification_name: "InferenceSpecificationName",
     #           environment_parameter_ranges: {
     #             categorical_parameter_ranges: [
@@ -4469,6 +4469,11 @@ module Aws::SageMaker
     #               },
     #             ],
     #           },
+    #           serverless_config: {
+    #             memory_size_in_mb: 1, # required
+    #             max_concurrency: 1, # required
+    #             provisioned_concurrency: 1,
+    #           },
     #         },
     #       ],
     #       volume_kms_key_id: "KmsKeyId",
@@ -4484,6 +4489,7 @@ module Aws::SageMaker
     #         nearest_model_name: "String",
     #         supported_instance_types: ["String"],
     #         data_input_config: "RecommendationJobDataInputConfig",
+    #         supported_endpoint_type: "RealTime", # accepts RealTime, Serverless
     #       },
     #       endpoints: [
     #         {
@@ -12296,6 +12302,9 @@ module Aws::SageMaker
     #   resp.input_config.endpoint_configurations[0].environment_parameter_ranges.categorical_parameter_ranges[0].name #=> String
     #   resp.input_config.endpoint_configurations[0].environment_parameter_ranges.categorical_parameter_ranges[0].value #=> Array
     #   resp.input_config.endpoint_configurations[0].environment_parameter_ranges.categorical_parameter_ranges[0].value[0] #=> String
+    #   resp.input_config.endpoint_configurations[0].serverless_config.memory_size_in_mb #=> Integer
+    #   resp.input_config.endpoint_configurations[0].serverless_config.max_concurrency #=> Integer
+    #   resp.input_config.endpoint_configurations[0].serverless_config.provisioned_concurrency #=> Integer
     #   resp.input_config.volume_kms_key_id #=> String
     #   resp.input_config.container_config.domain #=> String
     #   resp.input_config.container_config.task #=> String
@@ -12308,6 +12317,7 @@ module Aws::SageMaker
     #   resp.input_config.container_config.supported_instance_types #=> Array
     #   resp.input_config.container_config.supported_instance_types[0] #=> String
     #   resp.input_config.container_config.data_input_config #=> String
+    #   resp.input_config.container_config.supported_endpoint_type #=> String, one of "RealTime", "Serverless"
     #   resp.input_config.endpoints #=> Array
     #   resp.input_config.endpoints[0].endpoint_name #=> String
     #   resp.input_config.vpc_config.security_group_ids #=> Array
@@ -12326,10 +12336,14 @@ module Aws::SageMaker
     #   resp.inference_recommendations[0].metrics.model_latency #=> Integer
     #   resp.inference_recommendations[0].metrics.cpu_utilization #=> Float
     #   resp.inference_recommendations[0].metrics.memory_utilization #=> Float
+    #   resp.inference_recommendations[0].metrics.model_setup_time #=> Integer
     #   resp.inference_recommendations[0].endpoint_configuration.endpoint_name #=> String
     #   resp.inference_recommendations[0].endpoint_configuration.variant_name #=> String
     #   resp.inference_recommendations[0].endpoint_configuration.instance_type #=> String, one of "ml.t2.medium", "ml.t2.large", "ml.t2.xlarge", "ml.t2.2xlarge", "ml.m4.xlarge", "ml.m4.2xlarge", "ml.m4.4xlarge", "ml.m4.10xlarge", "ml.m4.16xlarge", "ml.m5.large", "ml.m5.xlarge", "ml.m5.2xlarge", "ml.m5.4xlarge", "ml.m5.12xlarge", "ml.m5.24xlarge", "ml.m5d.large", "ml.m5d.xlarge", "ml.m5d.2xlarge", "ml.m5d.4xlarge", "ml.m5d.12xlarge", "ml.m5d.24xlarge", "ml.c4.large", "ml.c4.xlarge", "ml.c4.2xlarge", "ml.c4.4xlarge", "ml.c4.8xlarge", "ml.p2.xlarge", "ml.p2.8xlarge", "ml.p2.16xlarge", "ml.p3.2xlarge", "ml.p3.8xlarge", "ml.p3.16xlarge", "ml.c5.large", "ml.c5.xlarge", "ml.c5.2xlarge", "ml.c5.4xlarge", "ml.c5.9xlarge", "ml.c5.18xlarge", "ml.c5d.large", "ml.c5d.xlarge", "ml.c5d.2xlarge", "ml.c5d.4xlarge", "ml.c5d.9xlarge", "ml.c5d.18xlarge", "ml.g4dn.xlarge", "ml.g4dn.2xlarge", "ml.g4dn.4xlarge", "ml.g4dn.8xlarge", "ml.g4dn.12xlarge", "ml.g4dn.16xlarge", "ml.r5.large", "ml.r5.xlarge", "ml.r5.2xlarge", "ml.r5.4xlarge", "ml.r5.12xlarge", "ml.r5.24xlarge", "ml.r5d.large", "ml.r5d.xlarge", "ml.r5d.2xlarge", "ml.r5d.4xlarge", "ml.r5d.12xlarge", "ml.r5d.24xlarge", "ml.inf1.xlarge", "ml.inf1.2xlarge", "ml.inf1.6xlarge", "ml.inf1.24xlarge", "ml.c6i.large", "ml.c6i.xlarge", "ml.c6i.2xlarge", "ml.c6i.4xlarge", "ml.c6i.8xlarge", "ml.c6i.12xlarge", "ml.c6i.16xlarge", "ml.c6i.24xlarge", "ml.c6i.32xlarge", "ml.g5.xlarge", "ml.g5.2xlarge", "ml.g5.4xlarge", "ml.g5.8xlarge", "ml.g5.12xlarge", "ml.g5.16xlarge", "ml.g5.24xlarge", "ml.g5.48xlarge", "ml.p4d.24xlarge", "ml.c7g.large", "ml.c7g.xlarge", "ml.c7g.2xlarge", "ml.c7g.4xlarge", "ml.c7g.8xlarge", "ml.c7g.12xlarge", "ml.c7g.16xlarge", "ml.m6g.large", "ml.m6g.xlarge", "ml.m6g.2xlarge", "ml.m6g.4xlarge", "ml.m6g.8xlarge", "ml.m6g.12xlarge", "ml.m6g.16xlarge", "ml.m6gd.large", "ml.m6gd.xlarge", "ml.m6gd.2xlarge", "ml.m6gd.4xlarge", "ml.m6gd.8xlarge", "ml.m6gd.12xlarge", "ml.m6gd.16xlarge", "ml.c6g.large", "ml.c6g.xlarge", "ml.c6g.2xlarge", "ml.c6g.4xlarge", "ml.c6g.8xlarge", "ml.c6g.12xlarge", "ml.c6g.16xlarge", "ml.c6gd.large", "ml.c6gd.xlarge", "ml.c6gd.2xlarge", "ml.c6gd.4xlarge", "ml.c6gd.8xlarge", "ml.c6gd.12xlarge", "ml.c6gd.16xlarge", "ml.c6gn.large", "ml.c6gn.xlarge", "ml.c6gn.2xlarge", "ml.c6gn.4xlarge", "ml.c6gn.8xlarge", "ml.c6gn.12xlarge", "ml.c6gn.16xlarge", "ml.r6g.large", "ml.r6g.xlarge", "ml.r6g.2xlarge", "ml.r6g.4xlarge", "ml.r6g.8xlarge", "ml.r6g.12xlarge", "ml.r6g.16xlarge", "ml.r6gd.large", "ml.r6gd.xlarge", "ml.r6gd.2xlarge", "ml.r6gd.4xlarge", "ml.r6gd.8xlarge", "ml.r6gd.12xlarge", "ml.r6gd.16xlarge", "ml.p4de.24xlarge", "ml.trn1.2xlarge", "ml.trn1.32xlarge", "ml.inf2.xlarge", "ml.inf2.8xlarge", "ml.inf2.24xlarge", "ml.inf2.48xlarge"
     #   resp.inference_recommendations[0].endpoint_configuration.initial_instance_count #=> Integer
+    #   resp.inference_recommendations[0].endpoint_configuration.serverless_config.memory_size_in_mb #=> Integer
+    #   resp.inference_recommendations[0].endpoint_configuration.serverless_config.max_concurrency #=> Integer
+    #   resp.inference_recommendations[0].endpoint_configuration.serverless_config.provisioned_concurrency #=> Integer
     #   resp.inference_recommendations[0].model_configuration.inference_specification_name #=> String
     #   resp.inference_recommendations[0].model_configuration.environment_parameters #=> Array
     #   resp.inference_recommendations[0].model_configuration.environment_parameters[0].key #=> String
@@ -17360,10 +17374,14 @@ module Aws::SageMaker
     #   resp.steps[0].inference_benchmark.metrics.model_latency #=> Integer
     #   resp.steps[0].inference_benchmark.metrics.cpu_utilization #=> Float
     #   resp.steps[0].inference_benchmark.metrics.memory_utilization #=> Float
+    #   resp.steps[0].inference_benchmark.metrics.model_setup_time #=> Integer
     #   resp.steps[0].inference_benchmark.endpoint_configuration.endpoint_name #=> String
     #   resp.steps[0].inference_benchmark.endpoint_configuration.variant_name #=> String
     #   resp.steps[0].inference_benchmark.endpoint_configuration.instance_type #=> String, one of "ml.t2.medium", "ml.t2.large", "ml.t2.xlarge", "ml.t2.2xlarge", "ml.m4.xlarge", "ml.m4.2xlarge", "ml.m4.4xlarge", "ml.m4.10xlarge", "ml.m4.16xlarge", "ml.m5.large", "ml.m5.xlarge", "ml.m5.2xlarge", "ml.m5.4xlarge", "ml.m5.12xlarge", "ml.m5.24xlarge", "ml.m5d.large", "ml.m5d.xlarge", "ml.m5d.2xlarge", "ml.m5d.4xlarge", "ml.m5d.12xlarge", "ml.m5d.24xlarge", "ml.c4.large", "ml.c4.xlarge", "ml.c4.2xlarge", "ml.c4.4xlarge", "ml.c4.8xlarge", "ml.p2.xlarge", "ml.p2.8xlarge", "ml.p2.16xlarge", "ml.p3.2xlarge", "ml.p3.8xlarge", "ml.p3.16xlarge", "ml.c5.large", "ml.c5.xlarge", "ml.c5.2xlarge", "ml.c5.4xlarge", "ml.c5.9xlarge", "ml.c5.18xlarge", "ml.c5d.large", "ml.c5d.xlarge", "ml.c5d.2xlarge", "ml.c5d.4xlarge", "ml.c5d.9xlarge", "ml.c5d.18xlarge", "ml.g4dn.xlarge", "ml.g4dn.2xlarge", "ml.g4dn.4xlarge", "ml.g4dn.8xlarge", "ml.g4dn.12xlarge", "ml.g4dn.16xlarge", "ml.r5.large", "ml.r5.xlarge", "ml.r5.2xlarge", "ml.r5.4xlarge", "ml.r5.12xlarge", "ml.r5.24xlarge", "ml.r5d.large", "ml.r5d.xlarge", "ml.r5d.2xlarge", "ml.r5d.4xlarge", "ml.r5d.12xlarge", "ml.r5d.24xlarge", "ml.inf1.xlarge", "ml.inf1.2xlarge", "ml.inf1.6xlarge", "ml.inf1.24xlarge", "ml.c6i.large", "ml.c6i.xlarge", "ml.c6i.2xlarge", "ml.c6i.4xlarge", "ml.c6i.8xlarge", "ml.c6i.12xlarge", "ml.c6i.16xlarge", "ml.c6i.24xlarge", "ml.c6i.32xlarge", "ml.g5.xlarge", "ml.g5.2xlarge", "ml.g5.4xlarge", "ml.g5.8xlarge", "ml.g5.12xlarge", "ml.g5.16xlarge", "ml.g5.24xlarge", "ml.g5.48xlarge", "ml.p4d.24xlarge", "ml.c7g.large", "ml.c7g.xlarge", "ml.c7g.2xlarge", "ml.c7g.4xlarge", "ml.c7g.8xlarge", "ml.c7g.12xlarge", "ml.c7g.16xlarge", "ml.m6g.large", "ml.m6g.xlarge", "ml.m6g.2xlarge", "ml.m6g.4xlarge", "ml.m6g.8xlarge", "ml.m6g.12xlarge", "ml.m6g.16xlarge", "ml.m6gd.large", "ml.m6gd.xlarge", "ml.m6gd.2xlarge", "ml.m6gd.4xlarge", "ml.m6gd.8xlarge", "ml.m6gd.12xlarge", "ml.m6gd.16xlarge", "ml.c6g.large", "ml.c6g.xlarge", "ml.c6g.2xlarge", "ml.c6g.4xlarge", "ml.c6g.8xlarge", "ml.c6g.12xlarge", "ml.c6g.16xlarge", "ml.c6gd.large", "ml.c6gd.xlarge", "ml.c6gd.2xlarge", "ml.c6gd.4xlarge", "ml.c6gd.8xlarge", "ml.c6gd.12xlarge", "ml.c6gd.16xlarge", "ml.c6gn.large", "ml.c6gn.xlarge", "ml.c6gn.2xlarge", "ml.c6gn.4xlarge", "ml.c6gn.8xlarge", "ml.c6gn.12xlarge", "ml.c6gn.16xlarge", "ml.r6g.large", "ml.r6g.xlarge", "ml.r6g.2xlarge", "ml.r6g.4xlarge", "ml.r6g.8xlarge", "ml.r6g.12xlarge", "ml.r6g.16xlarge", "ml.r6gd.large", "ml.r6gd.xlarge", "ml.r6gd.2xlarge", "ml.r6gd.4xlarge", "ml.r6gd.8xlarge", "ml.r6gd.12xlarge", "ml.r6gd.16xlarge", "ml.p4de.24xlarge", "ml.trn1.2xlarge", "ml.trn1.32xlarge", "ml.inf2.xlarge", "ml.inf2.8xlarge", "ml.inf2.24xlarge", "ml.inf2.48xlarge"
     #   resp.steps[0].inference_benchmark.endpoint_configuration.initial_instance_count #=> Integer
+    #   resp.steps[0].inference_benchmark.endpoint_configuration.serverless_config.memory_size_in_mb #=> Integer
+    #   resp.steps[0].inference_benchmark.endpoint_configuration.serverless_config.max_concurrency #=> Integer
+    #   resp.steps[0].inference_benchmark.endpoint_configuration.serverless_config.provisioned_concurrency #=> Integer
     #   resp.steps[0].inference_benchmark.model_configuration.inference_specification_name #=> String
     #   resp.steps[0].inference_benchmark.model_configuration.environment_parameters #=> Array
     #   resp.steps[0].inference_benchmark.model_configuration.environment_parameters[0].key #=> String
@@ -23848,7 +23866,7 @@ module Aws::SageMaker
         params: params,
         config: config)
       context[:gem_name] = 'aws-sdk-sagemaker'
-      context[:gem_version] = '1.193.0'
+      context[:gem_version] = '1.194.0'
       Seahorse::Client::Request.new(handlers, context)
     end
 

data/lib/aws-sdk-sagemaker/client_api.rb

@@ -963,6 +963,7 @@ module Aws::SageMaker
     InferenceRecommendationsJobs = Shapes::ListShape.new(name: 'InferenceRecommendationsJobs')
     InferenceSpecification = Shapes::StructureShape.new(name: 'InferenceSpecification')
     InferenceSpecificationName = Shapes::StringShape.new(name: 'InferenceSpecificationName')
+    InitialInstanceCount = Shapes::IntegerShape.new(name: 'InitialInstanceCount')
     InitialNumberOfUsers = Shapes::IntegerShape.new(name: 'InitialNumberOfUsers')
     InitialTaskCount = Shapes::IntegerShape.new(name: 'InitialTaskCount')
     InputConfig = Shapes::StructureShape.new(name: 'InputConfig')
@@ -1322,6 +1323,7 @@ module Aws::SageMaker
     ModelQualityBaselineConfig = Shapes::StructureShape.new(name: 'ModelQualityBaselineConfig')
     ModelQualityJobInput = Shapes::StructureShape.new(name: 'ModelQualityJobInput')
     ModelRegisterSettings = Shapes::StructureShape.new(name: 'ModelRegisterSettings')
+    ModelSetupTime = Shapes::IntegerShape.new(name: 'ModelSetupTime')
     ModelSortKey = Shapes::StringShape.new(name: 'ModelSortKey')
     ModelStepMetadata = Shapes::StructureShape.new(name: 'ModelStepMetadata')
     ModelSummary = Shapes::StructureShape.new(name: 'ModelSummary')
@@ -1616,6 +1618,7 @@ module Aws::SageMaker
     RecommendationJobStatus = Shapes::StringShape.new(name: 'RecommendationJobStatus')
     RecommendationJobStoppingConditions = Shapes::StructureShape.new(name: 'RecommendationJobStoppingConditions')
     RecommendationJobSupportedContentTypes = Shapes::ListShape.new(name: 'RecommendationJobSupportedContentTypes')
+    RecommendationJobSupportedEndpointType = Shapes::StringShape.new(name: 'RecommendationJobSupportedEndpointType')
     RecommendationJobSupportedInstanceTypes = Shapes::ListShape.new(name: 'RecommendationJobSupportedInstanceTypes')
     RecommendationJobType = Shapes::StringShape.new(name: 'RecommendationJobType')
     RecommendationJobVpcConfig = Shapes::StructureShape.new(name: 'RecommendationJobVpcConfig')
@@ -4968,9 +4971,10 @@ module Aws::SageMaker
     EndpointInput.add_member(:end_time_offset, Shapes::ShapeRef.new(shape: MonitoringTimeOffsetString, location_name: "EndTimeOffset"))
     EndpointInput.struct_class = Types::EndpointInput
 
-    EndpointInputConfiguration.add_member(:instance_type, Shapes::ShapeRef.new(shape: ProductionVariantInstanceType, required: true, location_name: "InstanceType"))
+    EndpointInputConfiguration.add_member(:instance_type, Shapes::ShapeRef.new(shape: ProductionVariantInstanceType, location_name: "InstanceType"))
     EndpointInputConfiguration.add_member(:inference_specification_name, Shapes::ShapeRef.new(shape: InferenceSpecificationName, location_name: "InferenceSpecificationName"))
     EndpointInputConfiguration.add_member(:environment_parameter_ranges, Shapes::ShapeRef.new(shape: EnvironmentParameterRanges, location_name: "EnvironmentParameterRanges"))
+    EndpointInputConfiguration.add_member(:serverless_config, Shapes::ShapeRef.new(shape: ProductionVariantServerlessConfig, location_name: "ServerlessConfig"))
     EndpointInputConfiguration.struct_class = Types::EndpointInputConfiguration
 
     EndpointInputConfigurations.member = Shapes::ShapeRef.new(shape: EndpointInputConfiguration)
@@ -4983,8 +4987,9 @@ module Aws::SageMaker
 
     EndpointOutputConfiguration.add_member(:endpoint_name, Shapes::ShapeRef.new(shape: String, required: true, location_name: "EndpointName"))
     EndpointOutputConfiguration.add_member(:variant_name, Shapes::ShapeRef.new(shape: String, required: true, location_name: "VariantName"))
-    EndpointOutputConfiguration.add_member(:instance_type, Shapes::ShapeRef.new(shape: ProductionVariantInstanceType, required: true, location_name: "InstanceType"))
-    EndpointOutputConfiguration.add_member(:initial_instance_count, Shapes::ShapeRef.new(shape: Integer, required: true, location_name: "InitialInstanceCount"))
+    EndpointOutputConfiguration.add_member(:instance_type, Shapes::ShapeRef.new(shape: ProductionVariantInstanceType, location_name: "InstanceType"))
+    EndpointOutputConfiguration.add_member(:initial_instance_count, Shapes::ShapeRef.new(shape: InitialInstanceCount, location_name: "InitialInstanceCount"))
+    EndpointOutputConfiguration.add_member(:serverless_config, Shapes::ShapeRef.new(shape: ProductionVariantServerlessConfig, location_name: "ServerlessConfig"))
     EndpointOutputConfiguration.struct_class = Types::EndpointOutputConfiguration
 
     EndpointPerformance.add_member(:metrics, Shapes::ShapeRef.new(shape: InferenceMetrics, required: true, location_name: "Metrics"))
@@ -7867,6 +7872,7 @@ module Aws::SageMaker
     RecommendationJobContainerConfig.add_member(:nearest_model_name, Shapes::ShapeRef.new(shape: String, location_name: "NearestModelName"))
     RecommendationJobContainerConfig.add_member(:supported_instance_types, Shapes::ShapeRef.new(shape: RecommendationJobSupportedInstanceTypes, location_name: "SupportedInstanceTypes"))
     RecommendationJobContainerConfig.add_member(:data_input_config, Shapes::ShapeRef.new(shape: RecommendationJobDataInputConfig, location_name: "DataInputConfig"))
+    RecommendationJobContainerConfig.add_member(:supported_endpoint_type, Shapes::ShapeRef.new(shape: RecommendationJobSupportedEndpointType, location_name: "SupportedEndpointType"))
     RecommendationJobContainerConfig.struct_class = Types::RecommendationJobContainerConfig
 
     RecommendationJobInferenceBenchmark.add_member(:metrics, Shapes::ShapeRef.new(shape: RecommendationMetrics, location_name: "Metrics"))
@@ -7924,6 +7930,7 @@ module Aws::SageMaker
     RecommendationMetrics.add_member(:model_latency, Shapes::ShapeRef.new(shape: Integer, required: true, location_name: "ModelLatency"))
     RecommendationMetrics.add_member(:cpu_utilization, Shapes::ShapeRef.new(shape: UtilizationMetric, location_name: "CpuUtilization"))
     RecommendationMetrics.add_member(:memory_utilization, Shapes::ShapeRef.new(shape: UtilizationMetric, location_name: "MemoryUtilization"))
+    RecommendationMetrics.add_member(:model_setup_time, Shapes::ShapeRef.new(shape: ModelSetupTime, location_name: "ModelSetupTime"))
     RecommendationMetrics.struct_class = Types::RecommendationMetrics
 
     RedshiftDatasetDefinition.add_member(:cluster_id, Shapes::ShapeRef.new(shape: RedshiftClusterId, required: true, location_name: "ClusterId"))

data/lib/aws-sdk-sagemaker/types.rb

@@ -2415,6 +2415,12 @@ module Aws::SageMaker
     # @!attribute [rw] time_series_forecasting_job_config
     #   Settings used to configure an AutoML job V2 for a time-series
     #   forecasting problem type.
+    #
+    #   <note markdown="1"> The `TimeSeriesForecastingJobConfig` problem type is only available
+    #   in private beta. Contact Amazon Web Services Support or your account
+    #   manager to learn more about access privileges.
+    #
+    #    </note>
     #   @return [Types::TimeSeriesForecastingJobConfig]
     #
     # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/AutoMLProblemTypeConfig AWS API Documentation
@@ -17129,12 +17135,17 @@ module Aws::SageMaker
     #   The parameter you want to benchmark against.
     #   @return [Types::EnvironmentParameterRanges]
     #
+    # @!attribute [rw] serverless_config
+    #   Specifies the serverless configuration for an endpoint variant.
+    #   @return [Types::ProductionVariantServerlessConfig]
+    #
     # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/EndpointInputConfiguration AWS API Documentation
     #
     class EndpointInputConfiguration < Struct.new(
       :instance_type,
       :inference_specification_name,
-      :environment_parameter_ranges)
+      :environment_parameter_ranges,
+      :serverless_config)
       SENSITIVE = []
       include Aws::Structure
     end
@@ -17196,13 +17207,18 @@ module Aws::SageMaker
     #   The number of instances recommended to launch initially.
     #   @return [Integer]
     #
+    # @!attribute [rw] serverless_config
+    #   Specifies the serverless configuration for an endpoint variant.
+    #   @return [Types::ProductionVariantServerlessConfig]
+    #
     # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/EndpointOutputConfiguration AWS API Documentation
     #
     class EndpointOutputConfiguration < Struct.new(
       :endpoint_name,
       :variant_name,
       :instance_type,
-      :initial_instance_count)
+      :initial_instance_count,
+      :serverless_config)
       SENSITIVE = []
       include Aws::Structure
     end
@@ -32884,6 +32900,17 @@ module Aws::SageMaker
     # @!attribute [rw] provisioned_concurrency
     #   The amount of provisioned concurrency to allocate for the serverless
     #   endpoint. Should be less than or equal to `MaxConcurrency`.
+    #
+    #   <note markdown="1"> This field is not supported for serverless endpoint recommendations
+    #   for Inference Recommender jobs. For more information about creating
+    #   an Inference Recommender job, see
+    #   [CreateInferenceRecommendationsJobs][1].
+    #
+    #    </note>
+    #
+    #
+    #
+    #   [1]: https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateInferenceRecommendationsJob.html
     #   @return [Integer]
     #
     # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/ProductionVariantServerlessConfig AWS API Documentation
@@ -34088,6 +34115,14 @@ module Aws::SageMaker
     #   [1]: https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_InputConfig.html#sagemaker-Type-InputConfig-DataInputConfig
     #   @return [String]
     #
+    # @!attribute [rw] supported_endpoint_type
+    #   The endpoint type to receive recommendations for. By default this is
+    #   null, and the results of the inference recommendation job return a
+    #   combined list of both real-time and serverless benchmarks. By
+    #   specifying a value for this field, you can receive a longer list of
+    #   benchmarks for the desired endpoint type.
+    #   @return [String]
+    #
     # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/RecommendationJobContainerConfig AWS API Documentation
     #
     class RecommendationJobContainerConfig < Struct.new(
@@ -34098,7 +34133,8 @@ module Aws::SageMaker
       :payload_config,
       :nearest_model_name,
       :supported_instance_types,
-      :data_input_config)
+      :data_input_config,
+      :supported_endpoint_type)
       SENSITIVE = []
       include Aws::Structure
     end
@@ -34422,6 +34458,14 @@ module Aws::SageMaker
     #   `NaN` indicates that the value is not available.
     #   @return [Float]
     #
+    # @!attribute [rw] model_setup_time
+    #   The time it takes to launch new compute resources for a serverless
+    #   endpoint. The time can vary depending on the model size, how long it
+    #   takes to download the model, and the start-up time of the container.
+    #
+    #   `NaN` indicates that the value is not available.
+    #   @return [Integer]
+    #
     # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/RecommendationMetrics AWS API Documentation
     #
     class RecommendationMetrics < Struct.new(
@@ -34430,7 +34474,8 @@ module Aws::SageMaker
       :max_invocations,
       :model_latency,
       :cpu_utilization,
-      :memory_utilization)
+      :memory_utilization,
+      :model_setup_time)
       SENSITIVE = []
       include Aws::Structure
     end
@@ -35012,10 +35057,15 @@ module Aws::SageMaker
     # endpoint.
     #
     # @!attribute [rw] maximum_batch_size
-    #   Batch size for each rolling step to provision capacity and turn on
-    #   traffic on the new endpoint fleet, and terminate capacity on the old
-    #   endpoint fleet. Value must be between 5% to 50% of the variant's
-    #   total instance count.
+    #   Specifies the type and size of the endpoint capacity to activate for
+    #   a blue/green deployment, a rolling deployment, or a rollback
+    #   strategy. You can specify your batches as either instance count or
+    #   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` to 100%, then SageMaker uses a
+    #   blue/green rollback strategy and rolls all traffic back to the blue
+    #   fleet.
     #   @return [Types::CapacitySize]
     #
     # @!attribute [rw] wait_interval_in_seconds
@@ -35029,12 +35079,15 @@ module Aws::SageMaker
     #   @return [Integer]
     #
     # @!attribute [rw] rollback_maximum_batch_size
-    #   Batch size for rollback to the old endpoint fleet. Each rolling step
-    #   to provision capacity and turn on traffic on the old endpoint fleet,
-    #   and terminate capacity on the new endpoint fleet. If this field is
-    #   absent, the default value will be set to 100% of total capacity
-    #   which means to bring up the whole capacity of the old fleet at once
-    #   during rollback.
+    #   Specifies the type and size of the endpoint capacity to activate for
+    #   a blue/green deployment, a rolling deployment, or a rollback
+    #   strategy. You can specify your batches as either instance count or
+    #   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` to 100%, then SageMaker uses a
+    #   blue/green rollback strategy and rolls all traffic back to the blue
+    #   fleet.
     #   @return [Types::CapacitySize]
     #
     # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/RollingUpdatePolicy AWS API Documentation

data/lib/aws-sdk-sagemaker.rb

@@ -53,6 +53,6 @@ require_relative 'aws-sdk-sagemaker/customizations'
 # @!group service
 module Aws::SageMaker
 
-  GEM_VERSION = '1.193.0'
+  GEM_VERSION = '1.194.0'
 
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: aws-sdk-sagemaker
 version: !ruby/object:Gem::Version
-  version: 1.193.0
+  version: 1.194.0
 platform: ruby
 authors:
 - Amazon Web Services
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2023-06-30 00:00:00.000000000 Z
+date: 2023-07-03 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: aws-sdk-core