Mojo module

dispatch

Dispatch for depth=512 pair-CTA SM100 (Blackwell) MHA prefill.

Creates the Depth512SM100Config, TMA tile descriptors, and launches the pair-CTA kernel with cluster_dim=(2,1,1). The TransientScheduler uses pair_cta=True so that both CTAs in a cluster derive the same tile index from block_idx.x >> 1.

comptime values

logger

comptime logger = Logger(stdout, prefix=String(""), source_location=False)

Functions

• ​mha_sm100_depth512_dispatch:

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