Skip to content

Release version 0.4.0
Compare
Choose a tag to compare
@volcacius volcacius released this 15 Mar 19:40
· 814 commits to master since this release
v0.4.0
691e79b

Changelog:

  • Add support for __torch_function__ to QuantTensor for supported versions of PyTorch. This finally removes the main barrier in making usage of QuantTensor more ingrained into the overall library.
  • Correctly export operators that are invoked through __torch_function__ and that are invariant to quantization such as torch.nn.functional.max_pool2d in both standard ONNX and PyXIR.
Assets 2
Loading