This is a patch release containing the following changes to v1.6.1:
- Implemented workaround for running examples using cmake on macOS (089a877)
- Implemented workaround for internal compiler error when building oneDNN with Microsoft Visual Studio 2019 (c6f9b7a)
- Fixed segfault for grouped convolutions (77e5d57)
- Fixed segfault for convolutions with 1x1 filter on Intel AVX2 systems (09c18e6)
- Fixed segfault for convolutions with 1x1 filter on Intel AVX-512 system (2c4ad38)
- Fixed issue with zero padding in bfloat16 convolutions with NHWC activations (4c05c18)