diff --git a/tests/quantization/test_compressed_tensors.py b/tests/quantization/test_compressed_tensors.py
index 0ca3df7e912..2620b679b6e 100644
--- a/tests/quantization/test_compressed_tensors.py
+++ b/tests/quantization/test_compressed_tensors.py
@@ -480,6 +480,7 @@ def test_compressed_tensors_fp8_block_enabled(vllm_runner):
             assert input_quant_op._forward_method in (
                 input_quant_op.forward_cuda,
                 input_quant_op.forward_hip,
+                input_quant_op.forward_xpu,
             )
 
         llm.apply_model(check_model)
diff --git a/vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py b/vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py
index 2231b2ca9af..229112739a4 100644
--- a/vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py
+++ b/vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py
@@ -396,7 +396,7 @@ class CompressedTensorsConfig(QuantizationConfig):
                     )
             return supported
         else:
-            return False
+            return not match_exact
 
     @staticmethod
     def _is_nvfp4_format(quant_args: QuantizationArgs):