`tf.reduce_join`: `reduction_indices` becomes `axis` * `tf.reduce_logsumexp`:
`reduction_indices` becomes `axis` * `tf.reduce_max`: `reduction_indices`
becomes `axis` * `tf.reduce_mean`: `reduction_indices` becomes `axis` *
`tf.reduce_min`: `reduction_indices` becomes `axis` * `tf.reduce_prod`:
`reduction_indices` becomes `axis` * `tf.reduce_sum`: `reduction_indices`

  //    // Eight-bit types don't require same operands and results scales.
  //    return bit_width != 8;
  //  }
  //}];
}

def TFL_ReduceMinOp: TFL_Op<"reduce_min", [
    PredOpTrait<"input and output must have same element type",
      TFL_TCresVTEtIsSameAsOp<0, 0>>,
    Pure,
    QuantizableResult,
    SameOperandsAndResultsScale]> {

values.

```python

  def stable_softmax(x):
    z = x - tf.reduce_max(x)
    numerator = tf.exp(z)
    denominator = tf.reduce_sum(numerator)
    return numerator / denominator
```

However, when we backprop through the softmax to x, we dont want to backprop
through the `tf.reduce_max(x)` (if the max values are not unique then the

    "SUM",
    "SQRT",
    "RSQRT",
    "SHAPE",
    "POW",
    "ARG_MIN",
    "FAKE_QUANT",
    "REDUCE_PROD",
    "REDUCE_MAX",
    "PACK",
    "LOGICAL_OR",
    "ONE_HOT",
    "LOGICAL_AND",
    "LOGICAL_NOT",
    "UNPACK",
    "REDUCE_MIN",
    "FLOOR_DIV",
    "REDUCE_ANY",
    "SQUARE",
    "ZEROS_LIKE",
    "FILL",
    "FLOOR_MOD",
    "RANGE",