delete comments of get_cache_scale in compressed_tensors.py

Signed-off-by: kewang-xlnx <kewang@xilinx.com>

vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py

@@ -412,10 +412,6 @@ def get_scheme(
         self._check_scheme_supported(scheme.get_min_capability())
         return scheme
 
-    # move the get_compressed_tensors_cache_scale method from
-    # utils.py to instance method of CompressedTensorsConfig
-    # class. By doing this, different QuantizationConfig
-    # classes can implement their own get_cache_scale method.
     def get_cache_scale(self, name: str) -> Optional[str]:
         """
         Check whether the param name matches the format for k/v cache scales