}
    result.emplace(std::move(outputs));
    return result;
  }
  std::vector<ParallelTensor*> parallel_inputs;
  std::vector<std::unique_ptr<ParallelTensor>> implicitly_broadcast_tensors;
  parallel_inputs.reserve(inputs.size());
  implicitly_broadcast_tensors.reserve(inputs.size());  // not tight
  for (const auto& input : inputs) {
    if (absl::holds_alternative<TFE_TensorHandle*>(input)) {