biondizzle ea648a9bc2 Fix NVFP4 mapper: keep model. prefix (model params use it)

2026-05-18 22:49:40 +00:00

..

patches

Fix NVFP4 mapper: keep model. prefix (model params use it)

2026-05-18 22:49:40 +00:00

cutedsl_quant_method.py

Fix: add abstract create_weights to CuTeDSLNvfp4LinearMethod

2026-05-18 20:40:48 +00:00

nvfp4_cutedsl.py

Fix torch.compile: use custom autograd Function instead of @torch.compiler.disable

2026-05-18 21:38:28 +00:00