biondizzle ecc7b83334 fix: compile CuTeDSL kernel with actual tensor shapes, not dummy 256x256 ...

The compiled kernel's TMA descriptors are sized based on compilation
shapes. Using dummy 256x256 shapes caused wrong memory access patterns
for the real 3584x6144 data. Now uses actual K_packed and N_packed
from the runtime tensors.

2026-05-16 19:58:13 +00:00

..

kernel

refactor: copy CuTeDSL kernel into repo with local imports

2026-05-16 02:57:54 +00:00

__init__.py

refactor: copy CuTeDSL kernel into repo with local imports

2026-05-16 02:57:54 +00:00

bridge.py

fix: compile CuTeDSL kernel with actual tensor shapes, not dummy 256x256

2026-05-16 19:58:13 +00:00

moe_pipeline.py

restore: new bridge/moe_pipeline/layertest

2026-05-16 19:55:19 +00:00