Properties (54)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
software
|
| gptkbp:availableIn |
AWS_cloud_services
|
| gptkbp:competesWith |
NVIDIA GPUs
|
| gptkbp:designedFor |
deep learning inference
|
| gptkbp:developedBy |
gptkb:Amazon_Web_Services
|
| gptkbp:enables |
scalable machine learning applications
|
| gptkbp:features |
multiple cores
|
| gptkbp:hasCapital |
processing large volumes of data
|
| https://www.w3.org/2000/01/rdf-schema#label |
AWS Inferentia
|
| gptkbp:integratesWith |
Amazon SageMaker
|
| gptkbp:isAvailableIn |
gptkb:AWS_Marketplace
multiple regions |
| gptkbp:isCompatibleWith |
gptkb:AWS_Lambda
Docker containers |
| gptkbp:isDesignedFor |
reduce latency
accelerate AI workloads cloud-based inference |
| gptkbp:isIntegratedWith |
AWS Deep Learning AMIs
|
| gptkbp:isOptimizedFor |
AI model deployment
|
| gptkbp:isPartOf |
AWS_ecosystem
AWS_AI_services AWS_Inferentia_chip_family AWS_machine_learning_portfolio |
| gptkbp:isPromotedBy |
AWS_marketing
|
| gptkbp:isPromotedThrough |
AWS_events
|
| gptkbp:isRated |
gptkb:AWS_Nitro_System
|
| gptkbp:isSuitableFor |
large datasets
|
| gptkbp:isSupportedBy |
AWS documentation
AWS_support_services |
| gptkbp:isTargetedAt |
developers
|
| gptkbp:isTestedFor |
various benchmarks
|
| gptkbp:isTrainedIn |
industry standards
|
| gptkbp:isUsedFor |
gptkb:Amazon_EC2
image recognition natural language processing recommendation systems |
| gptkbp:isUsedIn |
real-time applications
AI applications |
| gptkbp:isUtilizedFor |
data scientists
model optimization |
| gptkbp:isUtilizedIn |
automotive industry
financial services healthcare_applications |
| gptkbp:offers |
cost-effective inference
|
| gptkbp:performance |
machine learning workloads
|
| gptkbp:provides |
high performance
low latency high throughput |
| gptkbp:reduces |
inference costs
|
| gptkbp:releasedIn |
2019
|
| gptkbp:supports |
gptkb:ONNX
gptkb:PyTorch TensorFlow |
| gptkbp:uses |
custom silicon
|