Operation* filter_op = filter_value.getDefiningOp();
    auto filter_uniform_quantized_type =
        GetElementType(filter_value).cast<UniformQuantizedPerAxisType>();
    auto filter_constant_value_attr = cast<DenseIntElementsAttr>(
        cast<stablehlo::ConstantOp>(filter_value.getDefiningOp()).getValue());
    const DenseIntElementsAttr new_filter_value_attr =

  }

  // Get the tensor types.
  const auto input_type = input_tensor.getType().cast<ShapedType>();
  const auto weights_type = weights_tensor.getType().cast<ShapedType>();
  const auto bias_type =
      has_bias ? bias_tensor.getType().cast<ShapedType>() : ShapedType{};

  const auto output_type = getType(0).cast<ShapedType>();

  // Folding only implemented for float tensors.

    server.enqueue(
      MockResponse.Builder()
        .addHeader("Last-Modified: " + formatDate(-1, TimeUnit.HOURS))
        .addHeader("Expires: " + formatDate(1, TimeUnit.HOURS))
        .body("ABC")
        .build(),
    )
    server.enqueue(
      MockResponse.Builder()
        .addHeader("Last-Modified: " + formatDate(-5, TimeUnit.MINUTES))

                           array[i].cast<mlir::StringAttr>().getValue().str());
    } else if (llvm::isa<mlir::vhlo::BooleanV1Attr>(array[i])) {
      flex_builder->Bool(name.c_str(),
                         array[i].cast<mlir::vhlo::BooleanV1Attr>().getValue());
    } else if (llvm::isa<mlir::vhlo::StringV1Attr>(array[i])) {
      flex_builder->String(
          name.c_str(),

//===----------------------------------------------------------------------===//

LogicalResult BatchToSpaceNDOp::verify() {
  BatchToSpaceNDOp op = *this;
  auto block_shape_ty = mlir::cast<ShapedType>(op.getBlockShape().getType());
  auto crops_ty = mlir::cast<ShapedType>(op.getCrops().getType());

  if (block_shape_ty.hasStaticShape() && crops_ty.hasStaticShape()) {
    const int block_rank = block_shape_ty.getShape().front();

    if (!mlir::cast<ShapedType>(conv_op.getRhs().getType()).hasStaticShape()) {
      return false;
    }
    if (!mlir::cast<ShapedType>(conv_op.getLhs().getType()).hasStaticShape() &&
        !mlir::cast<ShapedType>(conv_op.getType()).hasStaticShape()) {
      auto dnums = conv_op.getDimensionNumbers();
      auto lhs_type = mlir::cast<ShapedType>(conv_op.getLhs().getType());

  }
}

LogicalResult SpaceToBatchNDOp::verify() {
  SpaceToBatchNDOp op = *this;
  const auto input_type = op.getInput().getType().cast<TensorType>();
  const auto block_shape_type = op.getBlockShape().getType().cast<TensorType>();
  const auto paddings_type = op.getPaddings().getType().cast<TensorType>();

  // Check that block_shape has rank 1.
  if (!IsOfRankOrUnranked(op.getBlockShape(), 1)) {

    /** The key of the message: Past 24 Hours */
    public static final String LABELS_facet_timestamp_1day = "{labels.facet_timestamp_1day}";

    /** The key of the message: Past Week */
    public static final String LABELS_facet_timestamp_1week = "{labels.facet_timestamp_1week}";

    /** The key of the message: Past Month */

// CHECK-LABEL: Tanh
// CHECK:  "tfl.tanh"(%arg0) : (tensor<1xf32>) -> tensor<1xf32>
}

func.func @cast(%arg0: tensor<1x2x2x5xi32>) -> tensor<1x2x2x5xf32> {
  %0 = "tf.Cast"(%arg0) : (tensor<1x2x2x5xi32>) -> tensor<1x2x2x5xf32>
  func.return %0 : tensor<1x2x2x5xf32>

  // CHECK-LABEL: cast
  // CHECK: "tfl.cast"(%arg0) : (tensor<1x2x2x5xi32>) -> tensor<1x2x2x5xf32>
}

			// there can be only one catch all egress listener with empty port, and it should be the last listener.
			if egress.Port == nil {
				if !catchAllEgressListenerFound {
					if index == len(rule.Egress)-1 {
						catchAllEgressListenerFound = true
					} else {
						errs = AppendValidation(errs, fmt.Errorf("sidecar: the egress listener with empty port should be the last listener in the list"))
					}
				} else {