[Misc] Fix get_min_capability (#5971)

2024-06-30 16:15:16 -04:00
parent deacb7ec44
commit 7836fdcc11
5 changed files with 17 additions and 6 deletions
--- a/vllm/model_executor/layers/quantization/base_config.py
+++ b/vllm/model_executor/layers/quantization/base_config.py
@@ -44,8 +44,9 @@ class QuantizationConfig(ABC):
        """List of supported activation dtypes."""
        raise NotImplementedError

+    @classmethod
    @abstractmethod
-    def get_min_capability(self) -> int:
+    def get_min_capability(cls) -> int:
        """Minimum GPU capability to support the quantization method.

        E.g., 70 for Volta, 75 for Turing, 80 for Ampere.