Specifies additional parameters for compiler options in JSON format. The compiler options are TargetPlatform specific. It is required for NVIDIA accelerators and highly recommended for CPU compilations. For any other cases, it is optional to specify CompilerOptions.
CPU: Compilation for CPU supports the following compiler options.
mcpu: CPU micro-architecture. For example, {'mcpu': 'skylake-avx512'}
mattr: CPU flags. For example, {'mattr': ['+neon', '+vfpv4']}
ARM: Details of ARM CPU compilations.
NEON: NEON is an implementation of the Advanced SIMD extension used in ARMv7 processors.
For example, add {'mattr': ['+neon']} to the compiler options if compiling for ARM 32-bit platform with the NEON support.
NVIDIA: Compilation for NVIDIA GPU supports the following compiler options.
gpu_code: Specifies the targeted architecture.
trt-ver: Specifies the TensorRT versions in x.y.z. format.
cuda-ver: Specifies the CUDA version in x.y format.
For example, {'gpu-code': 'sm_72', 'trt-ver': '6.0.1', 'cuda-ver': '10.1'}
ANDROID: Compilation for the Android OS supports the following compiler options:
ANDROID_PLATFORM: Specifies the Android API levels. Available levels range from 21 to 29. For example, {'ANDROID_PLATFORM': 28}.
mattr: Add {'mattr': ['+neon']} to compiler options if compiling for ARM 32-bit platform with NEON support.
INFERENTIA: Compilation for target ml_inf1 uses compiler options passed in as a JSON string. For example, \"CompilerOptions\": \"\\\"--verbose 1 --num-neuroncores 2 -O2\\\"\".
For information about supported compiler options, see Neuron Compiler CLI.
CoreML: Compilation for the CoreML OutputConfig$TargetDevice supports the following compiler options:
class_labels: Specifies the classification labels file name inside input tar.gz file. For example, {\"class_labels\": \"imagenet_labels_1000.txt\"}. Labels inside the txt file should be separated by newlines.
EIA: Compilation for the Elastic Inference Accelerator supports the following compiler options:
precision_mode: Specifies the precision of compiled artifacts. Supported values are \"FP16\" and \"FP32\". Default is \"FP32\".
signature_def_key: Specifies the signature to use for models in SavedModel format. Defaults is TensorFlow's default signature def key.
output_names: Specifies a list of output tensor names for models in FrozenGraph format. Set at most one API field, either: signature_def_key or output_names.
For example: {\"precision_mode\": \"FP32\", \"output_names\": [\"output:0\"]}
Specifies additional parameters for compiler options in JSON format. The compiler options are TargetPlatform specific. It is required for NVIDIA accelerators and highly recommended for CPU compilations. For any other cases, it is optional to specify CompilerOptions.
DTYPE: Specifies the data type for the input. When compiling for ml_* (except for ml_inf) instances using PyTorch framework, provide the data type (dtype) of the model's input. \"float32\" is used if \"DTYPE\" is not specified. Options for data type are:
float32: Use either \"float\" or \"float32\".
int64: Use either \"int64\" or \"long\".
For example, {\"dtype\" : \"float32\"}.
CPU: Compilation for CPU supports the following compiler options.
mcpu: CPU micro-architecture. For example, {'mcpu': 'skylake-avx512'}
mattr: CPU flags. For example, {'mattr': ['+neon', '+vfpv4']}
ARM: Details of ARM CPU compilations.
NEON: NEON is an implementation of the Advanced SIMD extension used in ARMv7 processors.
For example, add {'mattr': ['+neon']} to the compiler options if compiling for ARM 32-bit platform with the NEON support.
NVIDIA: Compilation for NVIDIA GPU supports the following compiler options.
gpu_code: Specifies the targeted architecture.
trt-ver: Specifies the TensorRT versions in x.y.z. format.
cuda-ver: Specifies the CUDA version in x.y format.
For example, {'gpu-code': 'sm_72', 'trt-ver': '6.0.1', 'cuda-ver': '10.1'}
ANDROID: Compilation for the Android OS supports the following compiler options:
ANDROID_PLATFORM: Specifies the Android API levels. Available levels range from 21 to 29. For example, {'ANDROID_PLATFORM': 28}.
mattr: Add {'mattr': ['+neon']} to compiler options if compiling for ARM 32-bit platform with NEON support.
INFERENTIA: Compilation for target ml_inf1 uses compiler options passed in as a JSON string. For example, \"CompilerOptions\": \"\\\"--verbose 1 --num-neuroncores 2 -O2\\\"\".
For information about supported compiler options, see Neuron Compiler CLI.
CoreML: Compilation for the CoreML OutputConfig$TargetDevice supports the following compiler options:
class_labels: Specifies the classification labels file name inside input tar.gz file. For example, {\"class_labels\": \"imagenet_labels_1000.txt\"}. Labels inside the txt file should be separated by newlines.
EIA: Compilation for the Elastic Inference Accelerator supports the following compiler options:
precision_mode: Specifies the precision of compiled artifacts. Supported values are \"FP16\" and \"FP32\". Default is \"FP32\".
signature_def_key: Specifies the signature to use for models in SavedModel format. Defaults is TensorFlow's default signature def key.
output_names: Specifies a list of output tensor names for models in FrozenGraph format. Set at most one API field, either: signature_def_key or output_names.
For example: {\"precision_mode\": \"FP32\", \"output_names\": [\"output:0\"]}
Set this to one of the following values:
Platform - The model image is hosted in Amazon ECR.
Vpc - The model image is hosted in a private Docker registry in your VPC.
Specifies an authentication configuration for the private docker registry where your model image is hosted. Specify a value for this property only if you specified Vpc as the value for the RepositoryAccessMode field of the ImageConfig object that you passed to a call to CreateModel and the private Docker registry where the model image is hosted requires authentication.
(Optional) Specifies an authentication configuration for the private docker registry where your model image is hosted. Specify a value for this property only if you specified Vpc as the value for the RepositoryAccessMode field, and the private Docker registry where the model image is hosted requires authentication.
The Amazon Resource Name (ARN) of an AWS Lambda function that provides credentials to authenticate to the private Docker registry where your model image is hosted. For information about how to create an AWS Lambda function, see Create a Lambda function with the console in the AWS Lambda Developer Guide.
" + } + }, "ResolvedAttributes": { "base": "The resolved attributes.
", "refs": { diff --git a/service/ec2/api.go b/service/ec2/api.go index c9525219cd9..541f544da7f 100644 --- a/service/ec2/api.go +++ b/service/ec2/api.go @@ -125162,6 +125162,33 @@ const ( // InstanceTypeMac1Metal is a InstanceType enum value InstanceTypeMac1Metal = "mac1.metal" + + // InstanceTypeX2gdMedium is a InstanceType enum value + InstanceTypeX2gdMedium = "x2gd.medium" + + // InstanceTypeX2gdLarge is a InstanceType enum value + InstanceTypeX2gdLarge = "x2gd.large" + + // InstanceTypeX2gdXlarge is a InstanceType enum value + InstanceTypeX2gdXlarge = "x2gd.xlarge" + + // InstanceTypeX2gd2xlarge is a InstanceType enum value + InstanceTypeX2gd2xlarge = "x2gd.2xlarge" + + // InstanceTypeX2gd4xlarge is a InstanceType enum value + InstanceTypeX2gd4xlarge = "x2gd.4xlarge" + + // InstanceTypeX2gd8xlarge is a InstanceType enum value + InstanceTypeX2gd8xlarge = "x2gd.8xlarge" + + // InstanceTypeX2gd12xlarge is a InstanceType enum value + InstanceTypeX2gd12xlarge = "x2gd.12xlarge" + + // InstanceTypeX2gd16xlarge is a InstanceType enum value + InstanceTypeX2gd16xlarge = "x2gd.16xlarge" + + // InstanceTypeX2gdMetal is a InstanceType enum value + InstanceTypeX2gdMetal = "x2gd.metal" ) // InstanceType_Values returns all elements of the InstanceType enum @@ -125556,6 +125583,15 @@ func InstanceType_Values() []string { InstanceTypeM6gd12xlarge, InstanceTypeM6gd16xlarge, InstanceTypeMac1Metal, + InstanceTypeX2gdMedium, + InstanceTypeX2gdLarge, + InstanceTypeX2gdXlarge, + InstanceTypeX2gd2xlarge, + InstanceTypeX2gd4xlarge, + InstanceTypeX2gd8xlarge, + InstanceTypeX2gd12xlarge, + InstanceTypeX2gd16xlarge, + InstanceTypeX2gdMetal, } } diff --git a/service/sagemaker/api.go b/service/sagemaker/api.go index 0216e7ebd6b..43848467e78 100644 --- a/service/sagemaker/api.go +++ b/service/sagemaker/api.go @@ -51052,6 +51052,13 @@ type ImageConfig struct { // // RepositoryAccessMode is a required field RepositoryAccessMode *string `type:"string" required:"true" enum:"RepositoryAccessMode"` + + // (Optional) Specifies an authentication configuration for the private docker + // registry where your model image is hosted. Specify a value for this property + // only if you specified Vpc as the value for the RepositoryAccessMode field, + // and the private Docker registry where the model image is hosted requires + // authentication. + RepositoryAuthConfig *RepositoryAuthConfig `type:"structure"` } // String returns the string representation @@ -51070,6 +51077,11 @@ func (s *ImageConfig) Validate() error { if s.RepositoryAccessMode == nil { invalidParams.Add(request.NewErrParamRequired("RepositoryAccessMode")) } + if s.RepositoryAuthConfig != nil { + if err := s.RepositoryAuthConfig.Validate(); err != nil { + invalidParams.AddNested("RepositoryAuthConfig", err.(request.ErrInvalidParams)) + } + } if invalidParams.Len() > 0 { return invalidParams @@ -51083,6 +51095,12 @@ func (s *ImageConfig) SetRepositoryAccessMode(v string) *ImageConfig { return s } +// SetRepositoryAuthConfig sets the RepositoryAuthConfig field's value. +func (s *ImageConfig) SetRepositoryAuthConfig(v *RepositoryAuthConfig) *ImageConfig { + s.RepositoryAuthConfig = v + return s +} + // A version of a SageMaker Image. A version represents an existing container // image. type ImageVersion struct { @@ -64274,6 +64292,12 @@ type OutputConfig struct { // and highly recommended for CPU compilations. For any other cases, it is optional // to specify CompilerOptions. // + // * DTYPE: Specifies the data type for the input. When compiling for ml_* + // (except for ml_inf) instances using PyTorch framework, provide the data + // type (dtype) of the model's input. "float32" is used if "DTYPE" is not + // specified. Options for data type are: float32: Use either "float" or "float32". + // int64: Use either "int64" or "long". For example, {"dtype" : "float32"}. + // // * CPU: Compilation for CPU supports the following compiler options. mcpu: // CPU micro-architecture. For example, {'mcpu': 'skylake-avx512'} mattr: // CPU flags. For example, {'mattr': ['+neon', '+vfpv4']} @@ -67864,6 +67888,56 @@ func (s *RenderingError) SetMessage(v string) *RenderingError { return s } +// Specifies an authentication configuration for the private docker registry +// where your model image is hosted. Specify a value for this property only +// if you specified Vpc as the value for the RepositoryAccessMode field of the +// ImageConfig object that you passed to a call to CreateModel and the private +// Docker registry where the model image is hosted requires authentication. +type RepositoryAuthConfig struct { + _ struct{} `type:"structure"` + + // The Amazon Resource Name (ARN) of an AWS Lambda function that provides credentials + // to authenticate to the private Docker registry where your model image is + // hosted. For information about how to create an AWS Lambda function, see Create + // a Lambda function with the console (https://docs.aws.amazon.com/lambda/latest/dg/getting-started-create-function.html) + // in the AWS Lambda Developer Guide. + // + // RepositoryCredentialsProviderArn is a required field + RepositoryCredentialsProviderArn *string `min:"1" type:"string" required:"true"` +} + +// String returns the string representation +func (s RepositoryAuthConfig) String() string { + return awsutil.Prettify(s) +} + +// GoString returns the string representation +func (s RepositoryAuthConfig) GoString() string { + return s.String() +} + +// Validate inspects the fields of the type to determine if they are valid. +func (s *RepositoryAuthConfig) Validate() error { + invalidParams := request.ErrInvalidParams{Context: "RepositoryAuthConfig"} + if s.RepositoryCredentialsProviderArn == nil { + invalidParams.Add(request.NewErrParamRequired("RepositoryCredentialsProviderArn")) + } + if s.RepositoryCredentialsProviderArn != nil && len(*s.RepositoryCredentialsProviderArn) < 1 { + invalidParams.Add(request.NewErrParamMinLen("RepositoryCredentialsProviderArn", 1)) + } + + if invalidParams.Len() > 0 { + return invalidParams + } + return nil +} + +// SetRepositoryCredentialsProviderArn sets the RepositoryCredentialsProviderArn field's value. +func (s *RepositoryAuthConfig) SetRepositoryCredentialsProviderArn(v string) *RepositoryAuthConfig { + s.RepositoryCredentialsProviderArn = &v + return s +} + // The resolved attributes. type ResolvedAttributes struct { _ struct{} `type:"structure"`