Skip to content

release(0.0.13):

Compare
Choose a tag to compare
@dacorvo dacorvo released this 23 Feb 17:11
· 364 commits to main since this release

New features

  • new QConv2d quantized module,
  • official support for float8 weights.

Bug fixes

  • fix QbitsTensor.to() that was not moving the inner tensors,
  • prevent shallow QTensor copies when loading weights that do not move inner tensors.