Skip to content

v2.4.4
Compare
Choose a tag to compare
@vpirogov vpirogov released this 15 Nov 20:30
· 6 commits to rls-v2.4 since this release
v2.4.4
145c4b5

This is a patch release containing the following changes to v2.4.3:

  • Fixed incorrect results for reorder with zero-points on CPUs (ee63629)
  • Fixed an issue with reorder with zero-points not respecting rounding mode on processors without Intel DL Boost support (a165c4a)
  • Fixed correctness issue in bfloat16 inner product weight gradient on processors with Intel DL Boost support (b782f19)
  • Improved bfloat16 inner product weights gradient performance on processors with Intel AMX support (ebf9f81)
  • Fixed potential undefined access in convolution, inner product, matmul, and RNNs primitives on processors with Intel AMX support (dcd98ad)
Assets 2
Loading