Why CUDAExecutionProvider doesn't support ConvInteger Op?

[lewisword]

Is your feature request related to a problem? Please describe.
When I want to execute ConvInteger quant comptation on GPU, I can't find support operation.

System information

• ONNX Runtime version (you are using): 1.4

Describe the solution you'd like
Support cuda version ConvInteger Op.

Describe alternatives you've considered
1.ConvInteger is a very common operation on cpu, gpu, arm and so on, I am little confused why CUDAExecutionProvider doesn't support ConvInteger Op.
2.Although I can use MatMulInteger and Img2col to complish the same work as ConvInteger can do, the former method is too slow.

[xxx554488]

I'm faced with the same problem. I have a custom training framework and I want to export to Onnx and excute on NV device by onnxruntime. But I just find there's no support operation for it.

[xxx554488]

@RyanUnderhill

[xiaodao2049]

I need this too. It's great if support execute on gpu.

[liuyuandong-qdml]

I need this stuff, too ==!

[yuslepukhin]

The simple answer to this: it was not implemented. We will certainly take this into account when prioritizing things. The fastest way for this remains is to submit a PR here.