Statements (28)
Predicate | Object |
---|---|
gptkbp:instanceOf |
machine learning accelerator
|
gptkbp:announced |
2018
|
gptkbp:architecture |
custom ASIC
|
gptkbp:availableOn |
AWS cloud
|
gptkbp:category |
AI hardware
|
gptkbp:designedFor |
machine learning inference
|
gptkbp:developedBy |
gptkb:Amazon_Web_Services
|
gptkbp:enables |
high throughput inference
low latency inference |
https://www.w3.org/2000/01/rdf-schema#label |
AWS Inferentia
|
gptkbp:integratesWith |
gptkb:AWS_Neuron_SDK
|
gptkbp:location |
gptkb:United_States
|
gptkbp:platform |
gptkb:TensorFlow
gptkb:MXNet gptkb:PyTorch |
gptkbp:successor |
gptkb:AWS_Inferentia2
|
gptkbp:supports |
BF16
FP16 INT8 |
gptkbp:usedBy |
gptkb:Amazon_Rekognition
gptkb:Amazon_Prime_Video gptkb:Amazon_Alexa |
gptkbp:usedFor |
deep learning inference workloads
|
gptkbp:usedIn |
gptkb:Amazon_EC2_Inf1_instances
|
gptkbp:bfsParent |
gptkb:SageMaker_Neo
gptkb:Radix-2_FFT gptkb:Amazon_Web_Services_AI |
gptkbp:bfsLayer |
6
|