biondizzle b06dcb40dc Fix MoE w1=None crash: keep shape-preserving dummy weights on CPU ...

The modular kernel framework reads w1.shape[0] in its outer apply()
before delegating to our expert impl. Setting layer.w13_weight = None
caused AttributeError. Replace with shape-preserving CPU dummy tensors
to free GPU memory while keeping shape metadata accessible.

2026-05-19 04:17:10 +00:00

..

kernels/linear/nvfp4

Replace autograd.Function with torch.library.custom_op for Dynamo compat

2026-05-19 01:54:48 +00:00

patches

Fix MoE w1=None crash: keep shape-preserving dummy weights on CPU

2026-05-19 04:17:10 +00:00

cutedsl_quant_method.py

Replace autograd.Function with torch.library.custom_op for Dynamo compat

2026-05-19 01:54:48 +00:00

nvfp4_cutedsl.py

Replace autograd.Function with torch.library.custom_op for Dynamo compat

2026-05-19 01:54:48 +00:00