Skip to content

PPQ v0.6.2

Compare
Choose a tag to compare
@ZhangZhiPku ZhangZhiPku released this 18 Mar 05:45
· 266 commits to master since this release
f435f35
  • Scale and offset are now always torch.Tensor with dtype=fp32 for training your network.
  • PPQ will display network snapshot when quantize your network.
  • Add brecq & lsq algorithms
  • Cuda kernels has been refined, more cuda kernels are introduced into ppq.
  • Add an exporter for dumping onnx quantization model.
  • Test cases are introduced here since ppq 0.6.2