[Performance] Missing CUDA Kernal for Pad, MaxPool, ConvTranspose opset 19-23

[AzHicham]

Describe the issue

Starting Opset 19 I have this missing cuda kernel

[I:onnxruntime:, cuda_execution_provider.cc:2922 GetCapability] CUDA kernel not found in registries for Op type: Pad node name: node_pad_3

And starting opset 22 I have both two more warning

[I:onnxruntime:, cuda_execution_provider.cc:2922 GetCapability] CUDA kernel not found in registries for Op type: MaxPool node name: node_max_pool2d_2
[I:onnxruntime:, cuda_execution_provider.cc:2922 GetCapability] CUDA kernel not found in registries for Op type: ConvTranspose node name: node_convolution_1

I don't know If there much difference introduced by Pad op19+ and MaxPool, ConvTranspose op23+ but it would be much appreciated to have kernel for thoses Ops

This is like #26075

To reproduce

NA

Urgency

No response

Platform

Linux

OS Version

Ubuntu 24.04

ONNX Runtime Installation

Released Package

ONNX Runtime Version or Commit ID

1.23.1

ONNX Runtime API

Python

Architecture

X64

Execution Provider

CUDA

Execution Provider Library Version

CUDA 12.9

Model File

No response

Is this a quantized model?

No

[skottmckay]

Pad-19 added a 'wrap' mode. We could register a kernel for that opset and fail if it uses the 'wrap' model. Not great but looks like that's what the CPU EP does anyway as it also lacks support for 'wrap'.
Pad-21/23/24 expanded the supported types but that wouldn't matter as the CUDA kernel is registered with specific types.

Maxpool-22 and ConvTranspose-22 added bfloat16 support. Should be fine to add that as the registration is typed (would not take a bfloat16 node)