Max - 12 vs 13

Next section compares an older to a newer version of the same operator after both definition are converted into markdown text. Green means an addition to the newer version, red means a deletion. Anything else is unchanged.

Files changed (1) hide show
  1. Max12 → Max13 +1 -1
Max12 → Max13 RENAMED
@@ -1 +1 @@
1
1
  Element-wise max of each of the input tensors (with Numpy-style broadcasting support).
2
2
  All inputs and outputs must have the same data type.
3
3
  This operator supports **multidirectional (i.e., Numpy-style) broadcasting**; for more details please check [Broadcasting in ONNX](https://github.com/onnx/onnx/blob/main/docs/Broadcasting.md).
4
4
  ### Inputs
5
5
  Between 1 and 2147483647 inputs.
6
6
  - **data_0** (variadic, heterogeneous) - **T**:
7
7
  List of tensors for max.
8
8
  ### Outputs
9
9
  - **max** (heterogeneous) - **T**:
10
10
  Output tensor.
11
11
  ### Type Constraints
12
- * **T** in ( tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8) ):
12
+ * **T** in ( tensor(bfloat16), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8) ):
13
13
  Constrain input and output types to numeric tensors.