Statements (24)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:software
|
| gptkbp:acceleration |
quantized neural networks
floating-point neural networks |
| gptkbp:developedBy |
gptkb:Google
|
| gptkbp:enables |
faster model execution
|
| https://www.w3.org/2000/01/rdf-schema#label |
XNNPACK Delegate
|
| gptkbp:integratesWith |
gptkb:TensorFlow_Lite_Interpreter
|
| gptkbp:license |
gptkb:Apache_License_2.0
|
| gptkbp:openSource |
true
|
| gptkbp:optimizedFor |
CPU inference
|
| gptkbp:purpose |
accelerate neural network inference
|
| gptkbp:repository |
https://github.com/google/XNNPACK
|
| gptkbp:supports |
gptkb:Android
gptkb:Windows gptkb:iOS gptkb:Linux mobile devices ARM CPUs edge devices x86 CPUs |
| gptkbp:usedIn |
gptkb:TensorFlow_Lite
|
| gptkbp:writtenBy |
gptkb:C++
|
| gptkbp:bfsParent |
gptkb:TensorFlow_Lite_Delegate
|
| gptkbp:bfsLayer |
7
|