Skip to main content

Mojo package

mha_depth512

Modules

  • barriers: Barrier infrastructure for depth=512 pair-CTA SM100 attention kernels.
  • config: Configuration for depth=512 pair-CTA SM100 (Blackwell) MHA kernels.
  • correction_warp: Correction warp group logic for depth=512 pair-CTA SM100 attention.
  • dispatch: Dispatch for depth=512 pair-CTA SM100 (Blackwell) MHA prefill.
  • kernel: Kernel entry point for depth=512 pair-CTA SM100 (Blackwell) MHA prefill.
  • load_warp: TMA load warp logic for depth=512 pair-CTA SM100 attention.
  • mma_warp: MMA warp logic for depth=512 pair-CTA SM100 attention.
  • smem: Shared memory layout for depth=512 pair-CTA SM100 attention kernels.
  • softmax_warp: Softmax warp group logic for depth=512 pair-CTA SM100 attention.

Was this page helpful?