TF_DerivedResultSizeAttr num_outputs = TF_DerivedResultSizeAttr<0>;
}

def TF_ReduceJoinOp : TF_Op<"ReduceJoin", [Pure]> {
  let summary = "Joins a string Tensor across the given dimensions.";

  let description = [{
Computes the string join across dimensions in the given string Tensor of shape
`[\\(d_0, d_1, ..., d_{n-1}\\)]`.  Returns a new Tensor created by joining the input

				strings.Join(missing.List(), "\n"))
		}
		if len(unexpected) > 0 {
			t.Errorf("the following fields were in the result, but unexpected. "+
				"If the field is new, please add it to the osNeutralFields set "+
				"or add it to the osSpecificFields set, as appropriate:\n%s",
				strings.Join(unexpected.List(), "\n"))
		}
	}
}

*   GPU
    *   GPU acceleration now supports quantized models by default
*   `DynamicBuffer::AddJoinedString()` will now add a separator if the first
    string to be joined is empty.
*   Adds support for cumulative sum (cumsum), both as builtin op and MLIR
    conversion.

### `TensorRT`

*   Issues a warning when the `session_config` parameter for the TF1 converter