}];

  let arguments = (ins
    TF_FpOrI32OrI64Tensor:$input,

    I64Attr:$group_size,
    I64Attr:$group_key,
    I64Attr:$instance_key,
    TF_AnyStrAttrOf<["Min", "Max", "Mul", "Add"]>:$merge_op,
    TF_AnyStrAttrOf<["Id", "Div"]>:$final_op,
    I64ArrayAttr:$subdiv_offsets,
    DefaultValuedOptionalAttr<I64ArrayAttr, "{}">:$wait_for,

    *   Unary GPU kernels: Abs, Atanh, Acos, Acosh, Asin, Asinh, Atan, Cos, Cosh, Sin, Sinh, Tan, Tanh.
    *   Binary GPU kernels: AddV2, Sub, Div, DivNoNan, Mul, MulNoNan, FloorDiv, Equal, NotEqual, Greater, GreaterEqual, LessEqual, Less.

* `tf.lite`
    * Add experimental supports conversion of models that may be larger than 2GB before buffer deduplication