[UX] Remove noisy CT UnquantizedLinearMethod warn (#33273)

Signed-off-by: mgoin <mgoin64@gmail.com>
2026-01-28 19:09:30 -05:00
parent 6bf3b46d78
commit 141cd43967
1 changed files with 1 additions and 5 deletions
--- a/vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py
+++ b/vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py
@@ -751,11 +751,7 @@ class CompressedTensorsConfig(QuantizationConfig):
                model_compression_config=model_compression_config,
            )
        elif weight_quant is None:
-            logger.warning_once(
-                "Acceleration for non-quantized schemes is "
-                "not supported by Compressed Tensors. "
-                "Falling back to UnquantizedLinearMethod"
-            )
+            # Falling back to UnquantizedLinearMethod
            return None

        else: