NVIDIA/cutlass v4.3.3

CUTLASS 4.3.3

on GitHub

CuTe DSL

• New features

  • Supported namedtuple and kwargs for JIT function arguments in tvm-ffi
  • Supported variadic tuples for JIT function argument in tvm-ffi

• Bug fixing and improvements

  • Fixed an issue when JIT function argument with union type annotation for tvm-ffi
  • Clearer error message for the case of runtime error cudaErrorInsufficientDriver