ONNX Runtime follows Semantic Versioning 2.0 for its public API. Each release has the form MAJOR.MINOR.PATCH, adhering to the definitions from the linked semantic versioning doc.
The version number of the current stable release can be found here.
All versions of ONNX Runtime will support ONNX opsets all the way back to (and including) opset version 7. In other words, if an ONNX Runtime release implements ONNX opset ver 9, it'll be able to run all models that are stamped with ONNX opset versions in the range [7-9].
The table summarizes the relationship between the ONNX Runtime version and the ONNX opset version implemented in that release. Please note the backward compatibility notes above. For more details on ONNX Release versions, see this page.
A variety of tools can be used to create ONNX models. 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 | Supported ONNX version(s) |
|---|---|---|
| PyTorch | Latest stable | 1.2-1.6 |
| ONNXMLTools CoreML, LightGBM, XGBoost, LibSVM |
Latest stable | 1.2-1.6 |
| ONNXMLTools SparkML |
Latest stable | 1.4-1.5 |
| SKLearn-ONNX | Latest stable | 1.2-1.6 |
| Keras-ONNX | Latest stable | 1.2-1.6 |
| Tensorflow-ONNX | Latest stable | 1.2-1.6 |
| WinMLTools | Latest stable | 1.2-1.6 |
| Paddle2ONNX | Latest stable | 1.6-1.9 |
| AutoML | 1.0.39+ | 1.5 |
| 1.0.33 | 1.4 |