RRDB_ESRGAN_vaiq_int8 model support

[AmosLewis]

Failed ops in mlir patch RRDB_ESRGAN_vaiq_int8.default.onnx.torch.elide.mlir

• https://github.com/nod-ai/SHARK-Turbine/issues/616

  %21858 = torch.operator "onnx.Resize"(%21853, %none, %21857) {torch.onnx.coordinate_transformation_mode = "asymmetric", torch.onnx.cubic_coeff_a = -7.500000e-01 : f32, torch.onnx.mode = "nearest", torch.onnx.nearest_mode = "floor"} : (!torch.vtensor<[1,64,224,224],f32>, !torch.none, !torch.vtensor<[4],f32>) -> !torch.vtensor<[?,?,?,?],f32>

  %21917 = torch.operator "onnx.Resize"(%21912, %none, %21916) {torch.onnx.coordinate_transformation_mode = "asymmetric", torch.onnx.cubic_coeff_a = -7.500000e-01 : f32, torch.onnx.mode = "nearest", torch.onnx.nearest_mode = "floor"} : (!torch.vtensor<[?,64,?,?],f32>, !torch.none, !torch.vtensor<[4],f32>) -> !torch.vtensor<[?,?,?,?],f32>

[zjgarvey]

This model will become blocked by an issue with an op interface applied during the pass memref::ResolveShapedTypeResultDimsPass I have a fix and will try to upstream.