its predecessor:

    ```mlir
    %outputs1:2, %control1 = tf_executor.island wraps "tf.IteratorGetNext"(%arg)
      {_class = ["loc:@dataset_iterator_1"]}
    %outputs2:2, %control2 = tf_executor.island wraps "tf.Split"(%outputs0, %outputs1#1)
      {_class = ["loc:@dataset_iterator_1", num_split = 2 : i32}
    ```
  }];
}

// `tfl.batch_matmul` when it accepts uniform quantized tensors.
//
// StableHLO Quantizer output:
//   * input: per-tensor qi8
//   * filter: per-channel qi8 for non-batching op, per-tensor for batching op.
//   * output: per-tensor qi32
// JAX Quantizer output:
//   * input: per-tensor qi8
//   * filter: per-channel qi8
//   * output: per-tensor qi8
//
// Conditions for the `tfl.batch_matmul` conversion: