This is the release note of v6.0.0. See here for the complete list of solved issues and merged PRs.

This release note only covers the difference from v6.0.0rc1; for all highlights and changes, please refer to the release notes of the pre-releases:

• alpha1
• beta1
• beta2
• beta3
• RC1

See the Upgrade Guide if you are upgrading from previous versions.

Bug Fixes

• Fix __cuda_array_interface__ data pointer for sliced arrays (#2134, thanks @pentschev!)
• Fix usage check of Tensor Core (#2172)
• Avoid using Tensor Core with cuDNN deterministic mode in convolution backward (#2176)

Code Fixes

• Avoid unnecessary weak pointer for null stream (#2154)

Documentation

• Add upgrade guide for v6 (#2187)

Installation

• Fix compile error on CUDA 10.1 and GCC 7 or 8 (#2160, thanks @grafi-tt!)

Tests

• Fix testing condition of diff and unwrap (#2142)