Statements (59)
| Predicate | Object |
|---|---|
| gptkbp:instance_of |
gptkb:software_framework
|
| gptkbp:bfsLayer |
3
|
| gptkbp:bfsParent |
gptkb:AWS
|
| gptkbp:allows |
model optimization
|
| gptkbp:can_be_used_with |
gptkb:Jupyter_notebooks
|
| gptkbp:developed_by |
gptkb:server
|
| gptkbp:enables |
deployment on edge devices
|
| gptkbp:enhances |
model portability
|
| gptkbp:facilitates |
scalable machine learning solutions
|
| https://www.w3.org/2000/01/rdf-schema#label |
Amazon Sage Maker Neo
|
| gptkbp:improves |
inference performance
|
| gptkbp:integrates_with |
gptkb:temple
|
| gptkbp:is_aimed_at |
enterprise customers
research institutions startups |
| gptkbp:is_available_in |
gptkb:AWS_Management_Console
multiple AWS regions |
| gptkbp:is_compatible_with |
gptkb:standard
gptkb:HIPAA gptkb:GDPR |
| gptkbp:is_designed_for |
developers and data scientists
|
| gptkbp:is_designed_to |
simplify machine learning workflows
|
| gptkbp:is_integrated_with |
gptkb:aircraft
gptkb:AWS_Io_T_Greengrass |
| gptkbp:is_optimized_for |
gptkb:ARM-based_processors
gptkb:AWS_Inferentia ONNX models NVIDIAGP Us Tensor Flow models Py Torch models MX Net models |
| gptkbp:is_part_of |
AWS ecosystem
AWSAI services |
| gptkbp:is_used_for |
machine learning model deployment
|
| gptkbp:is_used_in |
gptkb:financial_services_company
gptkb:Telecommunications_company healthcare manufacturing automotive gaming retail energy sector |
| gptkbp:offers |
monitoring capabilities
security features model compression |
| gptkbp:provides |
API access
data encryption model versioning logging features automatic model compilation support for multiple hardware platforms |
| gptkbp:reduces |
latency
|
| gptkbp:suitable_for |
gptkb:mobile_application
web applications Io T applications |
| gptkbp:supports |
multiple frameworks
real-time inference batch inference A/ B testing |