[Misc] Slight improvement of the BNB (#19418)

Signed-off-by: Jee Jee Li <[email protected]>
Co-authored-by: Isotr0py <[email protected]>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

Author: 3 people

vllm/model_executor/layers/quantization/bitsandbytes.py

@@ -71,9 +71,7 @@ def get_min_capability(cls) -> int:
 
     @staticmethod
     def get_config_filenames() -> list[str]:
-        return [
-            "adapter_config.json",
-        ]
+        return []
 
     @classmethod
     def from_config(cls, config: dict[str, Any]) -> "BitsAndBytesConfig":

vllm/model_executor/model_loader/bitsandbytes_loader.py

@@ -392,7 +392,8 @@ def _unquantized_generator(self, hf_weights_files, use_safetensors,
     def _get_bnb_target_modules(self, model: nn.Module) -> None:
 
         for name, module in model.named_modules():
-            if isinstance(module, (LinearBase, )):
+            if (isinstance(module, LinearBase) and
+                    hasattr(module.quant_method, "quant_config")):
                 if modules_info := self.modules_mapping.get_sub_modules(name):
                     # Map vllm's names to transformers's names.
                     rep_name, sub_modules = modules_info