becomes part of `outputs[partitions[js]]`.  The slices with `partitions[js] = i`
are placed in `outputs[i]` in lexicographic order of `js`, and the first
dimension of `outputs[i]` is the number of entries in `partitions` equal to `i`.
In detail,

```python
    outputs[i].shape = [sum(partitions == i)] + data.shape[partitions.ndim:]

    outputs[i] = pack([data[js, ...] for js if partitions[js] == i])

    key: "__saved_model_init_op"
    value {
      outputs {
        key: "__saved_model_init_op"
        value {
          name: "NoOp"
          tensor_shape {
            unknown_rank: true
          }
        }
      }
    }
  }
  signature_def {
    key: "serving_default"
    value {
      outputs {
        key: "output_0"
        value {
          name: "PartitionedCall:0"