IsWithinInt32Range);

    if (elements_all_in_int32_range) {
      std::vector<int32_t> output_shape(output_ty.getRank());
      std::transform(output_ty.getShape().begin(), output_ty.getShape().end(),
                     output_shape.begin(),
                     [](int64_t val) { return static_cast<int32_t>(val); });
      output_int_type = tensorflow::GetTypeFromTFTensorShape(

[i32, i32, i32, !tf_type.variant, !tf_type.variant, f32], _lower_using_switch_merge = true, _num_original_outputs = 6 : i64, _read_only_resource_inputs = [], body = @map_while_body_180, cond = @map_while_cond_170, device = "", is_stateless = true, output_shapes = [#tf_type.shape<>, #tf_type.shape<>, #tf_type.shape<>, #tf_type.shape<>, #tf_type.shape<>, #tf_type.shape<?>], parallel_iterations = 4 : i64, shape_invariant} : (tensor<i32>, tensor<i32>, tensor<i32>, tensor<!tf_type.variant<tensor<*xf32>>>,...

        all the TensorFlow OPs included in each of the `TRTEngineOp`s.

*   `tf.tpu.experimental.embedding`:

    *   `tf.tpu.experimental.embedding.FeatureConfig` now takes an additional
        argument `output_shape` which can specify the shape of the output
        activation for the feature.
    *   `tf.tpu.experimental.embedding.TPUEmbedding` now has the same behavior