Implementation of several NumPy dtype extensions
ml_dtypes is a stand-alone implementation of several NumPy dtype extensions used in machine learning libraries, including: bfloat16, 8-bit floating point representations, Microscaling (MX) sub-byte floating point representations, and Narrow integer encodings.
| Release | Stable | Testing |
|---|---|---|
| Fedora Rawhide | 0.5.4-1.fc45 | - |
You can contact the maintainers of this package via email at
python-ml-dtypes dash maintainers at fedoraproject dot org.