ttnn.maximum

ttnn.maximum = FastOperation(python_fully_qualified_name='ttnn.maximum', function=<ttnn._ttnn.operations.binary.maximum_t object>, preprocess_golden_function_inputs=<function default_preprocess_golden_function_inputs>, golden_function=<function _golden_function_maximum>, postprocess_golden_function_outputs=<function default_postprocess_golden_function_outputs>, is_cpp_operation=True, is_experimental=False)

Computes maximum for input_tensor_a and input_tensor_b and returns the tensor with the same layout as input_tensor_a

\[\mathrm{output\_tensor} = \verb|maximum|(\mathrm{input\_tensor\_a,input\_tensor\_b})\]

Args:

input_tensor_a (ttnn.Tensor): the input tensor. input_tensor_b (ttnn.Tensor or Number): the input tensor.

Keyword Args:

memory_config (ttnn.MemoryConfig, optional): memory configuration for the operation. Defaults to None.

Returns:

ttnn.Tensor: the output tensor.

Note:

Supported dtypes, layouts, and ranks:

Dtypes	Layouts	Ranks
BFLOAT16, BFLOAT8_B	TILE	2, 3, 4

Example:

>>> tensor1 = ttnn.from_torch(torch.tensor([[1, 2], [3, 4]], dtype=torch.bfloat16), layout=ttnn.TILE_LAYOUT, device=device)
>>> tensor2 = ttnn.from_torch(torch.tensor([[1, 2], [3, 4]], dtype=torch.bfloat16), layout=ttnn.TILE_LAYOUT, device=device)
>>> output = ttnn.maximum(tensor1, tensor2/scalar)