biondizzle 6626b75a2f fix: use filter_zeros for SF allocation + no-branch forward mapping ...

- Allocation: cute::size(cute::filter_zeros(layout)) matches CUTLASS examples
- Kernel: layout_sf(make_coord(mn, k_sf*16, 0)) — no branching on LayoutRank
- Avoids silent fallthrough that wrote dst[0] for all threads

2026-05-15 22:58:51 +00:00

..

nvfp4_megamoe_kernel

fix: use filter_zeros for SF allocation + no-branch forward mapping

2026-05-15 22:58:51 +00:00

nvfp4_megamoe_kernel.egg-info

feat: CUTLASS NVFP4 mega_moe kernel — slot-based L1/L2, source-first SF remap

2026-05-15 11:38:18 +00:00