使用from onnxruntime.quantization import quantize_dynamic, QuantType将onnx模型量化为int8，但是在使用atc工具转换为om模型时产生错误。部分错误信息如下：

ATC run failed, Please check the detail log, Try 'atc --help' for more information 

E19010: No parser is registered for Op [/encoder/embed/Unsqueeze_output_0_QuantizeLinear, optype [ai.onnx::11::DynamicQuantizeLinear]]. 

        Solution: Check the version of the installation package and reinstall the package. For details, see the operator specifications. 

        TraceBack (most recent call last): 

        No parser is registered for Op [/encoder/embed/conv/conv.0/Conv_quant, optype [ai.onnx::11::ConvInteger]]. 

        No parser is registered for Op [/encoder/embed/conv/conv.1/Relu_output_0_QuantizeLinear, optype [ai.onnx::11::DynamicQuantizeLinear]]. 

        No parser is registered for Op [/encoder/embed/conv/conv.2/Conv_quant, optype [ai.onnx::11::ConvInteger]]. 

        No parser is registered for Op [/encoder/embed/Reshape_output_0_QuantizeLinear, optype [ai.onnx::11::DynamicQuantizeLinear]].

Model parse to graph failed, graph name:anon_encoder_int8.[FUNC:ModelParseToGraph][FILE:onnx_parser.cc][LINE:925] 

        ATC model parse ret fail.[FUNC:ParseGraph][FILE:omg.cc][LINE:780]

但是，使用from onnxmltools.utils.float16_converter import convert_float_to_float16量化的onnx模型就可以成功使用atc转换为om模型，请问问题出在了哪里？