blib/lib/Paws/SageMaker/ProductionVariant.pm untested

filter: Statementstmt 0.0% 0 / 10 Branchbran n/a Conditioncond n/a MC/DCmcdc n/a Subroutinesub 0.0% 0 / 1 Podpod n/a totaltotal 0.0% 0 / 11 CC 1 SCAR 6.9
CC
1
Cov
0%
BEGIN
2.0
CRAP 2.0
1 # Generated by default/object.tt
2 package Paws::SageMaker::ProductionVariant;
3 use Moose;
4 has AcceleratorType => (is => 'ro', isa => 'Str');
5 has CoreDumpConfig => (is => 'ro', isa => 'Paws::SageMaker::ProductionVariantCoreDumpConfig');
6 has InitialInstanceCount => (is => 'ro', isa => 'Int', required => 1);
7 has InitialVariantWeight => (is => 'ro', isa => 'Num');
8 has InstanceType => (is => 'ro', isa => 'Str', required => 1);
9 has ModelName => (is => 'ro', isa => 'Str', required => 1);
10 has VariantName => (is => 'ro', isa => 'Str', required => 1);
11  
12 1;
13  
14 ### main pod documentation begin ###
15  
16 =head1 NAME
17  
18 Paws::SageMaker::ProductionVariant
19  
20 =head1 USAGE
21  
22 This class represents one of two things:
23  
24 =head3 Arguments in a call to a service
25  
26 Use the attributes of this class as arguments to methods. You shouldn't make instances of this class.
27 Each attribute should be used as a named argument in the calls that expect this type of object.
28  
29 As an example, if Att1 is expected to be a Paws::SageMaker::ProductionVariant object:
30  
31 $service_obj->Method(Att1 => { AcceleratorType => $value, ..., VariantName => $value });
32  
33 =head3 Results returned from an API call
34  
35 Use accessors for each attribute. If Att1 is expected to be an Paws::SageMaker::ProductionVariant object:
36  
37 $result = $service_obj->Method(...);
38 $result->Att1->AcceleratorType
39  
40 =head1 DESCRIPTION
41  
42 Identifies a model that you want to host and the resources chosen to
43 deploy for hosting it. If you are deploying multiple models, tell
44 Amazon SageMaker how to distribute traffic among the models by
45 specifying variant weights.
46  
47 =head1 ATTRIBUTES
48  
49  
50 =head2 AcceleratorType => Str
51  
52 The size of the Elastic Inference (EI) instance to use for the
53 production variant. EI instances provide on-demand GPU computing for
54 inference. For more information, see Using Elastic Inference in Amazon
55 SageMaker (https://docs.aws.amazon.com/sagemaker/latest/dg/ei.html).
56  
57  
58 =head2 CoreDumpConfig => L<Paws::SageMaker::ProductionVariantCoreDumpConfig>
59  
60 Specifies configuration for a core dump from the model container when
61 the process crashes.
62  
63  
64 =head2 B<REQUIRED> InitialInstanceCount => Int
65  
66 Number of instances to launch initially.
67  
68  
69 =head2 InitialVariantWeight => Num
70  
71 Determines initial traffic distribution among all of the models that
72 you specify in the endpoint configuration. The traffic to a production
73 variant is determined by the ratio of the C<VariantWeight> to the sum
74 of all C<VariantWeight> values across all ProductionVariants. If
75 unspecified, it defaults to 1.0.
76  
77  
78 =head2 B<REQUIRED> InstanceType => Str
79  
80 The ML compute instance type.
81  
82  
83 =head2 B<REQUIRED> ModelName => Str
84  
85 The name of the model that you want to host. This is the name that you
86 specified when creating the model.
87  
88  
89 =head2 B<REQUIRED> VariantName => Str
90  
91 The name of the production variant.
92  
93  
94  
95 =head1 SEE ALSO
96  
97 This class forms part of L<Paws>, describing an object used in L<Paws::SageMaker>
98  
99 =head1 BUGS and CONTRIBUTIONS
100  
101 The source code is located here: L<https://github.com/pplu/aws-sdk-perl>
102  
103 Please report bugs to: L<https://github.com/pplu/aws-sdk-perl/issues>
104  
105 =cut
106