Skip to content

CUTLASS 3.2.1
Compare
Choose a tag to compare
@hwu36 hwu36 released this 26 Sep 21:47
· 145 commits to main since this release
v3.2.1
5cd735c
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Learn about vigilant mode.
  • Python support SM90 Epilogue Visitor Tree (EVT) on top of the C++ support released in 3.2.0.
  • SM80 EVT support in C++ and Python.
  • Other SM90 epilogue improvements.
  • Splitting CUTLASS library into smaller units based on operation, arch and datatypes. See #1105 for details.
  • Making tools/library/scripts packageable - tools/library/scripts is now moving to python/cutlass_library. See the Python README for details.
  • SM90 TF32 kernel improvements for all layouts.
  • SM90 rasterization direction support in the CUTLASS profiler.
  • Improvement for CUTLASS profiler build times.
  • Remove Python-C++ bindings.
Assets 2
Loading
0 Join discussion