Remove ScaledActivation for AWQ (#10057)

Signed-off-by: mgoin <michael@neuralmagic.com>
2024-11-06 09:27:06 -05:00
parent 406d4cc480
commit 399c798608
34 changed files with 19 additions and 124 deletions
--- a/vllm/model_executor/layers/quantization/fp8.py
+++ b/vllm/model_executor/layers/quantization/fp8.py
@@ -92,9 +92,6 @@ class Fp8Config(QuantizationConfig):
            return Fp8KVCacheMethod(self)
        return None

-    def get_scaled_act_names(self) -> List[str]:
-        return []
-

 class Fp8LinearMethod(LinearMethodBase):
    """Linear method for FP8.