ONNX Runtime compatibility

Contents

Backwards compatibility

Newer versions of ONNX Runtime support all models that worked with prior versions, so updates should not break integrations.

Environment compatibility

ONNX Runtime is not explicitly tested with every variation/combination of environments and dependencies, so this list is not comprehensive. Please use this as starting reference. For specific questions or requests, please file an issue on Github.

Platforms

  • Windows

    • Tested with Windows 10 and Windows Server 2019
    • May be compatible with Windows 7+
    • Windows Machine Learning (Windows)
      • CPU: Windows 8.1+
      • GPU: Windows 10 1709+
  • Linux
  • Mac
    • Tested with 10.14 (Mojave)
    • May be compatible with 10.12+ (Sierra)
  • Android
    • Tested with API level 28 (v9 “Pie”)
    • May be compatible with API level 21+ (v5 “Lollipop”)
  • iOS
    • Tested with iOS 12
    • May be compatible with any 64bit iOS version (5S+)

Compilers

  • Windows 10: Visual C++ 2019
  • Linux: gcc>=4.8

Dependent Libraries

ONNX opset support

ONNX Runtime supports all opsets from the latest released version of the ONNX spec. All versions of ONNX Runtime support ONNX opsets from ONNX v1.2.1+ (opset version 7 and higher).

ONNX Runtime version ONNX version ONNX opset version ONNX ML opset version ONNX IR version Windows ML Availability
1.16 1.14.1 19 3 9 Windows AI 1.16+
1.15 1.14 19 3 8 Windows AI 1.15+
1.14 1.13 18 3 8 Windows AI 1.14+
1.13 1.12 17 3 8 Windows AI 1.13+
1.12 1.12 17 3 8 Windows AI 1.12+
1.11 1.11 16 2 8 Windows AI 1.11+
1.10 1.10 15 2 8 Windows AI 1.10+
1.9 1.10 15 2 8 Windows AI 1.9+
1.8 1.9 14 2 7 Windows AI 1.8+
1.7 1.8 13 2 7 Windows AI 1.7+
1.6 1.8 13 2 7 Windows AI 1.6+
1.5 1.7 12 2 7 Windows AI 1.5+
1.4 1.7 12 2 7 Windows AI 1.4+
1.3 1.7 12 2 7 Windows AI 1.3+
1.2
1.1
1.6 11 2 6 Windows AI 1.3+
1.0 1.6 11 2 6 Windows AI 1.3+
0.5 1.5 10 1 5 Windows AI 1.3+
0.4 1.5 10 1 5 Windows AI 1.3+
0.3 1.4 9 1 3 Windows 10 2004+
0.2 1.3 8 1 3 Windows 10 1903+
0.1 1.3 8 1 3 Windows 10 1809+

Unless otherwise noted, please use the latest released version of the tools to convert/export the ONNX model. Most tools are backwards compatible and support multiple ONNX versions. Join this with the table above to evaluate ONNX Runtime compatibility.

Tool Recommended Version
PyTorch Latest stable
Tensorflow-ONNX Latest stable
ONNXMLTools
CatBoost, CoreML, LightGBM, XGBoost, LibSVM, SparkML
Latest stable
SKLearn-ONNX Latest stable
WinMLTools Latest stable
AzureML AutoML 1.0.39+ (ONNX v1.5)
1.0.33 (ONNX v1.4)
Paddle2ONNX Latest stable