biondizzle b0b5113467 Fix weight mapper: compressor → attn.compressor (not mla_attn), quant weights_proj ...

- The compressor is on attn.compressor (not attn.mla_attn.compressor)
- weights_proj in indexer is NVFP4-quantized in our checkpoint

2026-05-19 03:20:41 +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 weight mapper: compressor → attn.compressor (not mla_attn), quant weights_proj

2026-05-19 03:20:41 +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