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/bitsandbytes.py
+++ b/vllm/model_executor/layers/quantization/bitsandbytes.py
@@ -114,9 +114,6 @@ class BitsAndBytesConfig(QuantizationConfig):
            return BitsAndBytesLinearMethod(self)
        return None

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

 def is_layer_skipped_bnb(prefix: str, llm_int8_skip_modules: List[str]):
    # Split the prefix into its dot-separated components