github NVIDIA/cutlass v4.6.2
CUTLASS 4.6.2

3 hours ago

CuTe DSL

  • Bug fixing and improvements
    • Reverted the TMA bulk copy elect_one change from 4.6.0 to reset the behavior to align with 4.5.x releases
    • Fixed a vectorized fp32->f8 conversion issue (!3382)
    • Fixed a CuTe DSL fp8 grouped_gemm_dglu kernel compilation issue (!397)
    • Fixed opt-level setting issue for ptxas (!3389)
    • set_name_prefix of kernel now supports full customization on compiled kernel name (!3389)
    • Fixed issue in (!3349)
    • Fixed issue in (!3351)
    • Reduced JIT compile overhead by ~50 ms per cute.compile
    • Speed up importing cutlass.cute by 3.8x with Torch installed, 1.25x without.

This release has been tested against the following packages:

Don't miss a new cutlass release

NewReleases is sending notifications on new releases.