errors using qViT.onnx to do inference

[yuhuixu1993]

With no modification，I using your ptq code to export deit onnx models. But error occurs when using onnxruntime to inference the onnx model.

onnxruntime.capi.onnxruntime_pybind11_state.InvalidGraph: [ONNXRuntimeError] : 10 : INVALID_GRAPH : This is an invalid model. Error in Node:QuantizeLinear_2 : No Op registered for QuantizeLinear with domain_version of 13

[yuhuixu1993]

I solve this problem by upgrading CUDA and onnxruntime, however, the quantized model is much slower than fp16