Mojo module

mma_sm100

SM100 (Blackwell) matrix multiply operations (deprecated - use gpu.compute.arch.mma_nvidia_sm100).

This module is deprecated. For new code, import from the gpu.compute.arch.mma_nvidia_sm100 module instead:

# Deprecated:
from gpu.mma_sm100 import mma, UMMAKind, UMMAInsDescriptor

# Recommended:
from gpu.compute.arch.mma_nvidia_sm100 import mma, UMMAKind, UMMAInsDescriptor

This module provides NVIDIA Blackwell (SM100) specific tensor core operations including unified MMA (UMMA) instructions.

Was this page helpful?

Thank you! We'll create more content like this.

Thank you for helping us improve!

😔 What went wrong?

Some code doesn’t work

It includes inaccurate information

It's missing information I need

It was difficult to understand

Other

Submit