biondizzle 4cf5b8b751 Fix compressor path: attn.mla_attn.compressor (not attn.compressor) ...

The compressor is inside mla_attn, not directly on the attention wrapper.
Debug output confirmed: layers.0.attn.mla_attn.compressor.fused_wkv_wgate.*

2026-05-19 03:47:26 +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 compressor path: attn.mla_attn.compressor (not attn.compressor)

2026-05-19 03:47:26 +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