ONNX Runtime
E814638
ONNX Runtime is a high-performance, cross-platform inference engine for running machine learning models in the Open Neural Network Exchange (ONNX) format across a variety of hardware and deployment environments.
Statements (58)
| Predicate | Object |
|---|---|
| instanceOf |
deep learning runtime
ⓘ
machine learning inference engine ⓘ open-source software ⓘ |
| developer | Microsoft ⓘ |
| feature |
ONNX model compatibility
ⓘ
cross-platform support ⓘ graph optimizations ⓘ hardware acceleration ⓘ high-performance inference ⓘ model optimization ⓘ quantization support ⓘ training support ⓘ |
| license | MIT License ⓘ |
| partOf | ONNX ecosystem NERFINISHED ⓘ |
| programmingLanguage |
C
ⓘ
C# NERFINISHED ⓘ C++ ⓘ Java ⓘ JavaScript ⓘ Objective-C NERFINISHED ⓘ Python ⓘ Swift NERFINISHED ⓘ |
| relatedTo | ONNX NERFINISHED ⓘ |
| repository | https://github.com/microsoft/onnxruntime ⓘ |
| supportsExecutionProvider |
CPUExecutionProvider
GENERATED
ⓘ
CUDA GENERATED ⓘ CoreML GENERATED ⓘ DirectML GENERATED ⓘ DmlExecutionProvider GENERATED ⓘ OpenVINO GENERATED ⓘ ROCm GENERATED ⓘ TensorRT GENERATED ⓘ |
| supportsFormat | ONNX NERFINISHED ⓘ |
| supportsHardware |
CPU
ⓘ
FPGA ⓘ GPU ⓘ NPU ⓘ VPU NERFINISHED ⓘ |
| supportsLanguageBinding |
C API
NERFINISHED
ⓘ
C# API ⓘ Java API NERFINISHED ⓘ JavaScript API NERFINISHED ⓘ Objective-C API NERFINISHED ⓘ Python API NERFINISHED ⓘ Swift API NERFINISHED ⓘ |
| supportsPlatform |
Android
ⓘ
Azure NERFINISHED ⓘ Edge devices ⓘ Linux ⓘ Web ⓘ Windows ⓘ iOS ⓘ macOS ⓘ |
| useCase |
cloud deployment
ⓘ
edge deployment ⓘ on-device AI ⓘ production inference ⓘ |
| website | https://onnxruntime.ai ⓘ |
Referenced by (2)
Full triples — surface form annotated when it differs from this entity's canonical label.