Statements (20)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:cloud_service
|
| gptkbp:allows |
selection of GPU acceleration amount
|
| gptkbp:billingModel |
pay-as-you-go
|
| gptkbp:category |
AI/ML service
|
| gptkbp:compatibleWith |
gptkb:Amazon_SageMaker
gptkb:Amazon_ECS gptkb:Amazon_EKS |
| gptkbp:enables |
attachment of GPU-powered inference acceleration to EC2 instances
|
| https://www.w3.org/2000/01/rdf-schema#label |
AWS Elastic Inference
|
| gptkbp:launched |
2018
|
| gptkbp:provides |
gptkb:Amazon_Web_Services
|
| gptkbp:reduces |
cost of deep learning inference
|
| gptkbp:regionAvailability |
multiple AWS regions
|
| gptkbp:supports |
gptkb:TensorFlow
gptkb:Apache_MXNet gptkb:ONNX |
| gptkbp:usedFor |
machine learning inference
|
| gptkbp:website |
https://aws.amazon.com/machine-learning/elastic-inference/
|
| gptkbp:bfsParent |
gptkb:PrivateLink
|
| gptkbp:bfsLayer |
6
|