[Feature Request] How should I use symmetric quantization to quantify weight and obtain the correct quantization model?

[cosonjia]

Describe the feature request

Describe the bug:

I am able to do quantization with:

quantized_model = quantize_dynamic(
        model_input=model_input,
        model_output=model_output,
        # optimize_model=False,
        weight_type=QuantType.QInt8, 
        # activation_type=QuantType.QInt8,
        # op_types_to_quantize=["Conv", "MatMul", "Add","Relu"], 
        extra_options={"UseSymmetric": True, "ActivationSymmetric": True, 
                       "EnableSubgraph": True, "ForceQuantizeNoInputCheck": True}  
    )

but I got the following error while doing the inference:

File "/home/pc10/anaconda3/envs/evo-venv/lib/python3.11/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 465, in init
self._create_inference_session(providers, provider_options, disabled_optimizers)
File "/home/pc10/anaconda3/envs/evo-venv/lib/python3.11/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 537, in _create_inference_session
sess.initialize_session(providers, provider_options, disabled_optimizers)
onnxruntime.capi.onnxruntime_pybind11_state.NotImplemented: [ONNXRuntimeError] : 9 : NOT_IMPLEMENTED : Could not find an implementation for ConvInteger(10) node with name 'Conv__116_quant'

System information

OS Platform and Distribution: Ubuntu Ubuntu 20.04.5 LTS(5.15.0-48-generic)
CPU 12th Gen Intel(R) Core(TM) i9-12900K
ONNX Runtime installed by pip:
ONNX Runtime version: 1.20.1
Python version: 3.11.11

How should I use symmetric quantization to quantify weight and obtain the correct quantization model?

Describe scenario use case

quantized_model = quantize_dynamic(
        model_input=model_input,
        model_output=model_output,
        # optimize_model=False,
        weight_type=QuantType.QInt8, 
        # activation_type=QuantType.QInt8,
        # op_types_to_quantize=["Conv", "MatMul", "Add","Relu"], 
        extra_options={"UseSymmetric": True, "ActivationSymmetric": True, 
                       "EnableSubgraph": True, "ForceQuantizeNoInputCheck": True}  
    )