}
    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)) {

*   Added colocation constraints to `StagingArea`.
*   `sparse_matmul_op` reenabled for Android builds.
*   Restrict weights rank to be the same as the broadcast target, to avoid
    ambiguity on broadcast rules.
*   Upgraded libxsmm to 1.7.1 and applied other changes for performance and
    memory usage.
*   Fixed bfloat16 integration of LIBXSMM sparse mat-mul.