%cst_0 = "tf.Const"() {value = dense<0.400000e+00> : tensor<2x2xf32>} : () -> tensor<2x2xf32>
  %0 = "tf.Conv2D"(%arg0, %cst) {data_format = "NHWC", dilations = [1, 1, 2, 1], explicit_paddings = [], padding = "SAME", strides = [1, 1, 2, 1], use_cudnn_on_gpu = true} : (tensor<1x3x4x3xf32>, tensor<2x3x3x2xf32>) -> tensor<1x3x2x2xf32>
  %1 = "tf.Mul"(%0, %cst_0) : (tensor<1x3x2x2xf32>, tensor<2x2xf32>) -> tensor<1x3x2x2xf32>
  func.return %1 : tensor<1x3x2x2xf32>
}

  // CHECK-SAME: %[[ARG0:.*]]: tensor<3x2xf32>
  // CHECK-SAME: %[[ARG1:.*]]: tensor<1x2xf32>
  // CHECK-SAME: %[[ARG2:.*]]: tensor<2x5xf32>
  func.func private @concatenate_and_composite(%arg0: tensor<3x2xf32>, %arg1: tensor<1x2xf32>, %arg2: tensor<2x5xf32>) -> tensor<4x5xf32> {
    // CHECK: %[[Q1:.*]] = "quantfork.qcast"(%[[ARG0]]) {volatile} : (tensor<3x2xf32>) -> tensor<3x2x!quant.uniform<i8:f32, 5.000000e-03:-1>>

  %4 = "tfl.dequantize"(%3) : (tensor<32x12x!quant.uniform<u8<1:255>:f32, 0.021826678373682216:151>>) -> tensor<32x12xf32>
  %5 = "tfl.fully_connected"(%2, %4, %cst) {fused_activation_function = "NONE", keep_num_dims = false, weights_format = "DEFAULT"} : (tensor<1x224x224x3xf32>, tensor<32x12xf32>, tensor<32xf32>) -> tensor<1x112x112x32xf32>

    func.return %1 : tensor<2x!tf_type.qint32>
}

// -----

// CHECK-LABEL: func @while_region_qint
func.func @while_region_qint(%arg0: tensor<2x2xf32>) -> (tensor<2x?xf32>, tensor<?x2xf32>) {
  %scales = "tf.Const"() { value = dense<1.0> : tensor<f32> } : () -> tensor<f32>
  %zps2 = "tf.Const"() { value = dense<2> : tensor<i32> } : () -> tensor<i32>

    device = "", dim_args_spec = [], disabled_checks = [],
    has_token_input_output = false, module = "", platforms = [],
    version = 5 : i64
  } : (tensor<2x2xf32>, tensor<2x3xf32>) -> tensor<2x3xf32>
  %2 = stablehlo.add %cst, %0 : tensor<2x3xf32>
  return %2 : tensor<2x3xf32>
}

// CHECK-LABEL: func.func @no_qdq_for_multiple_users
// CHECK-NOT: quantfork.qcast

    %2:2 = "tf.RecvTPUEmbeddingActivations"() {_tpu_embedding_layer = "call1", config = "\0A\0B\0C\0D"} : () -> (tensor<2x2xf32>, tensor<4x4xf32>)
    "tf.SendTPUEmbeddingGradients"(%2#0, %2#1) {_tpu_embedding_layer = "call1", config = "\0A\0B\0C\0D", operandSegmentSizes = array<i32: 2, 0>} : (tensor<2x2xf32>, tensor<4x4xf32>) -> ()
    tf_device.return