biondizzle 057ae2101e CRITICAL FIX: Move tiled_mma creation and _setup_attributes OUTSIDE @cute.jit ...

The _setup_attributes() calls cute.size(tiled_mma.shape_mnk, mode=[2])
which requires host-side execution. Inside @cute.jit, tiled_mma.shape_mnk
returns MLIR values that can't be unpacked by cute.size().

This follows the fused_swiglu.py pattern exactly: setup on host side,
then pass everything to the kernel. Removed @cute.jit wrapper entirely
in favor of direct kernel launch (same as fused_swiglu).

2026-06-01 10:28:01 +00:00

..

cache

E1: Wire LayerCacheHandle gather methods + CUDA gather kernels

2026-05-30 21:09:21 +00:00

kernels

CRITICAL FIX: Move tiled_mma creation and _setup_attributes OUTSIDE @cute.jit

2026-06-01 10:28:01 +00:00

layers

Wire NVFP4 fused router kernel into e2e single-shot pipeline

2026-06-01 09:47:48 +00:00

loader

Restructure: cutedsl/ -> dsv4/ with proper layering

2026-05-21 17:30:44 +00:00

model

Fix remaining mHC API references: layer_compare.py, layer.py comment

2026-05-31 18:38:34 +00:00

ops

fix: clamp block_amax to E4M3 max (448) in quantize_activation_nvfp4 — prevents NaN from overflow

2026-06-01 04:59:06 +00:00

reference

Restructure: cutedsl/ -> dsv4/ with proper layering

2026-05-21 17:30:44 +00:00

__init__.py

Restructure: cutedsl/ -> dsv4/ with proper layering

2026-05-21 17:30:44 +00:00