Skip to content

Release 1.3.0
Compare
Choose a tag to compare
@lior-dikstein lior-dikstein released this 20 Sep 08:11
· 42 commits to main since this release
v1.3.0
612741a

What's Changed

  • TensorFlow 2.13 and .keras File Format Support: MCT Quantizers now offers full compatibility with TensorFlow version 2.13 and the .keras file format.
  • MCT Quantizers Version Tracking. With this release, you can easily access the 'mctq_version' property within each KerasQuantizationWrapper and KerasActivationQuantizationHolder.
  • Support ONNX models export- we now support exporting models to the ONNX format. Notice this is experimental and subject to future changes.

Breaking Changes

  • LUT Quantizer Argument Improvements: We've refined the argument names for the Look-Up Table (LUT) quantizer.

Contributors

@ofirgo @reuvenperetz @Chizkiyahu @eladc-git @lior-dikstein

New Contributors

Full Changelog: v1.2.0...v1.3.0

Contributors

ofirgo, Chizkiyahu, and 3 other contributors
Assets 2
Loading