biondizzle 1528d4e182 Fix NVFP4 mapper: strip model. prefix from checkpoint keys ...

The NVFP4 checkpoint uses model.layers.* but vLLM's AutoWeightsLoader
expects layers.* (relative to the model module). Strip the model. prefix
instead of adding it.

2026-05-18 22:46:04 +00:00

..

patches

Fix NVFP4 mapper: strip model. prefix from checkpoint keys

2026-05-18 22:46:04 +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