[Quant] [Bugfix] Fix quantization config matching with hf_to_vllm_mapper (#20046)

This commit is contained in:
Kyle Sayers
2025-07-01 19:20:34 +09:00
committed by GitHub
parent c05596f1a3
commit 9025a9a705
17 changed files with 107 additions and 29 deletions
@@ -181,6 +181,7 @@ class ModelOptNvFp4Config(QuantizationConfig):
exclude_modules: list[str],
group_size: int = 16,
) -> None:
super().__init__()
self.is_checkpoint_nvfp4_serialized = is_checkpoint_nvfp4_serialized
if is_checkpoint_nvfp4_serialized:
logger.warning(