718ca7f920
* Fix PR #5550 reverted in #5911 (performance improvment for operator Transpose) (#5916) * Improves implementation of transpose operator * Fix issue mentioned in #5911 * adding unit test for function DoTransposeImpl * Make operator TreeEnsemble 5x faster for batches of size 100.000 (#5965) * improves processing time by 10 * extend coverage unit test coverage * better implementation for the multi regression case * better comment, keep parallelization by trees when not enough trees * Initialize a structure in operator ReduceSum (#6005) * fix initialisation issue * Fuse MatMulIntegerToFloat only when scales are scalar (#6008) MatMulIntegerToFloat fusion fuses per-row and per-column MatMulInteger, which is not supported by the MatMulIntegerToFloat kernel now. Limit the fusion to per-matrix only before we supporting the per-channel fully. * Disable Python 3.9 for training Python packaging build. (#6012) Disable Python 3.9 for training Python packaging build. Python 3.9 is not supported by the PyTorch dependency. * Fix bugs for 1: Calibrator should check model inputs; 2: (#6017) quantize_inupts forgot to use parameter initializer_use_weight_qtyp. * Bump highlight.js from 10.2.1 to 10.4.1 in /nodejs Bumps [highlight.js](https://github.com/highlightjs/highlight.js) from 10.2.1 to 10.4.1. - [Release notes](https://github.com/highlightjs/highlight.js/releases) - [Changelog](https://github.com/highlightjs/highlight.js/blob/master/CHANGES.md) - [Commits](https://github.com/highlightjs/highlight.js/compare/10.2.1...10.4.1) Signed-off-by: dependabot[bot] <support@github.com> * work around of the build break in mac (#6069) * Fix the build break in macos release * revert android change * Bump up API version for 1.6 release (#6076) * Update version to 1.6.0 (#6041) * Update version to 1.6.0 * Add v 1.5.3 info * Updating WindowsAI and ONNX version Co-authored-by: Du Li <duli@OrtTrainingDev0.af05slrtruoetgaxwwjv5nsq5e.px.internal.cloudapp.net> * Rsevert "Fuse MatMulIntegerToFloat only when scales are scalar (#6008)" This reverts commit beb950eb66308eeaa8c60e4db9a006948e2ba7bb. Co-authored-by: Xavier Dupré <xadupre@users.noreply.github.com> Co-authored-by: Yufeng Li <liyufeng1987@gmail.com> Co-authored-by: Edward Chen <18449977+edgchen1@users.noreply.github.com> Co-authored-by: Zhang Lei <zhang.huanning@hotmail.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Pranav Sharma <prs@microsoft.com> Co-authored-by: Du Li <duli@OrtTrainingDev0.af05slrtruoetgaxwwjv5nsq5e.px.internal.cloudapp.net>
3.8 KiB
Versioning
API
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.
Current stable release version
The version number of the current stable release can be found here.
Release cadence
Compatibility
Backwards compatibility
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].
Version matrix
The following 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.
| ONNX Runtime release version | ONNX release version | ONNX opset version | ONNX ML opset version | Supported ONNX IR version | Windows ML Availability |
|---|---|---|---|---|---|
| 1.6.0 | 1.8 down to 1.2 | 13 | 2 | 7 | Windows AI 1.6+ |
| 1.5.3 | 1.7 down to 1.2 | 12 | 2 | 7 | Windows AI 1.5+ |
| 1.5.2 | 1.7 down to 1.2 | 12 | 2 | 7 | Windows AI 1.5+ |
| 1.5.1 | 1.7 down to 1.2 | 12 | 2 | 7 | Windows AI 1.5+ |
| 1.4.0 | 1.7 down to 1.2 | 12 | 2 | 7 | Windows AI 1.4+ |
| 1.3.1 | 1.7 down to 1.2 | 12 | 2 | 7 | Windows AI 1.4+ |
| 1.3.0 | 1.7 down to 1.2 | 12 | 2 | 7 | Windows AI 1.3+ |
| 1.2.0 1.1.2 1.1.1 1.1.0 |
1.6 down to 1.2 | 11 | 2 | 6 | Windows AI 1.3+ |
| 1.0.0 | 1.6 down to 1.2 | 11 | 2 | 6 | Windows AI 1.3+ |
| 0.5.0 | 1.5 down to 1.2 | 10 | 1 | 5 | Windows AI 1.3+ |
| 0.4.0 | 1.5 down to 1.2 | 10 | 1 | 5 | Windows AI 1.3+ |
| 0.3.1 0.3.0 |
1.4 down to 1.2 | 9 | 1 | 3 | Windows 10 2004+ |
| 0.2.1 0.2.0 |
1.3 down to 1.2 | 8 | 1 | 3 | Windows 10 1903+ |
| 0.1.5 0.1.4 |
1.3 down to 1.2 | 8 | 1 | 3 | Windows 10 1809+ |
Tool Compatibility
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 |
| AutoML | 1.0.39+ | 1.5 |
| 1.0.33 | 1.4 |