NVIDIA/cutlass v4.5.2

CUTLASS 4.5.2

on GitHub

CuTe DSL

• New features

  • Python 3.14t is now supported with GIL enabled

• Bug fixing and improvements

  • Fixed following issues:
    #3240
    #3241

CUTLASS C++

• Fix missing convert fucntion in EVT for fp4 kernels.
• Avoid instantiate 2sm tma kernels where ctaN is none power of 64 when ctaN > 128 in profiler.