For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /max/get-started.md).

Mojo module

blockwise_fp8_1d2d_smem

Shared memory layout for blockwise FP8 1D2D SM100 matmul.

This is a simplified SMEM structure for the 1D2D blockwise FP8 kernel that uses offset-based addressing (GroupedWorkIterator1D1D). Key differences from the standard BlockwiseFP8Smem:

1. No CLC pipeline storage - uses 3-warp specialization (no scheduler warp)
2. Uses SmemPipelineBundleNoClc instead of SmemPipelineBundle
3. Otherwise identical tile storage (A, B, C, A-scales)

Tile storage is shared via BlockwiseFP8TileCore from blockwise_fp8_smem.mojo.

Structs

• ​BlockwiseFP8_1D2DSmem: SMEM struct for blockwise FP8 1D2D matmul without CLC scheduler.

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