// If no padding is negative return the input as is.
    if (llvm::all_of(explicit_padding, [](int64_t pad) { return pad >= 0; })) {
      return value;
    }

    auto input_type = mlir::cast<RankedTensorType>(value.getType());
    auto input_shape = input_type.getShape();

    llvm::SmallVector<int64_t, 4> start;
    llvm::SmallVector<int64_t, 4> size;
    start.reserve(explicit_padding.size() / 2);

                                   *index);
  }
  return absl::OkStatus();
}

// Returns the data type of the destination of an edge.
DataType EdgeType(const Edge* edge) {
  return edge->dst()->input_type(edge->dst_input());
}

// Adds the control inputs of `node` to `*deps`.
void AddControlInputs(const Node& node, absl::flat_hash_set<Node*>* deps) {
  for (const Edge* edge : node.in_edges()) {

	1, // 1: istio.networking.nds.v1.NameTable.TableEntry.value:type_name -> istio.networking.nds.v1.NameTable.NameInfo
	2, // [2:2] is the sub-list for method output_type
	2, // [2:2] is the sub-list for method input_type
	2, // [2:2] is the sub-list for extension type_name
	2, // [2:2] is the sub-list for extension extendee
	0, // [0:2] is the sub-list for field type_name
}

func init() { file_dns_proto_nds_proto_init() }

                        const bool enable_per_channel_quantized_weight) {
  const GemmStyleOp gemm_style_op =
      *entry_func_op.getOps<GemmStyleOp>().begin();

  const Type input_type = entry_func_op.getArgumentTypes()[0];
  const Type filter_type = entry_func_op.getArgumentTypes()[1];
  const Type func_result_type = entry_func_op.getResultTypes()[0];

  if (inserted) {
    NodeDef arg_def;
    NodeDefBuilder builder(
        absl::StrCat(src_node->name(), "_", src_slot, "_arg"), kArgOp,
        NodeDebugInfo(src_node->def()));
    DataType dtype = edge->dst()->input_type(edge->dst_input());
    builder.Attr("T", dtype);
    builder.Attr("index", arg_index);
    Status s = builder.Finalize(&arg_def);
    if (!s.ok()) return s;

TFR_BUILTINS = {
    '_tfr_quant_act_range': (TFRTypes.TENSOR, TFRTypes.TENSOR),
    '_tfr_quant_rescale': TFRTypes.TENSOR,
    '_tfr_quant_raw_data': lambda input_type: input_type,
    '_tfr_quant_qparam': (TFRTypes.TENSOR, TFRTypes.TENSOR),
    '_tfr_quant_scale_factor': TFRTypes.TENSOR,
}


class TFRTypeResolver(type_inference.Resolver):

  }
  if (grad_inputs.size() != 1) {
    return errors::InvalidArgument("Tile grad requires 1 grad input");
  }

  Shape::Attrs shape_attrs;
  shape_attrs.out_type_ = op.input_type(1);
  auto input_shape = Shape(scope, op.input(0), shape_attrs);
  // We interleave multiples and input_shape to get split_shape,
  // reshape grad to split_shape, and reduce along all even

	7, // 6: istio.workload.zds.WorkloadResponse.ack:type_name -> istio.workload.zds.Ack
	7, // [7:7] is the sub-list for method output_type
	7, // [7:7] is the sub-list for method input_type
	7, // [7:7] is the sub-list for extension type_name
	7, // [7:7] is the sub-list for extension extendee
	0, // [0:7] is the sub-list for field type_name
}

func init() { file_zdsapi_zds_proto_init() }

	8,  // 13: istio.security.StringMatch.presence:type_name -> google.protobuf.Empty
	14, // [14:14] is the sub-list for method output_type
	14, // [14:14] is the sub-list for method input_type
	14, // [14:14] is the sub-list for extension type_name
	14, // [14:14] is the sub-list for extension extendee
	0,  // [0:14] is the sub-list for field type_name
}

	7, // 9: proto.EchoTestService.ForwardEcho:output_type -> proto.ForwardEchoResponse
	8, // [8:10] is the sub-list for method output_type
	6, // [6:8] is the sub-list for method input_type
	6, // [6:6] is the sub-list for extension type_name
	6, // [6:6] is the sub-list for extension extendee
	0, // [0:6] is the sub-list for field type_name
}

func init() { file_test_echo_proto_echo_proto_init() }