ttnn.addalpha

ttnn.addalpha(input_tensor_a: ttnn.Tensor, input_tensor_b: ttnn.Tensor, alpha: float, *, memory_config: ttnn.MemoryConfig | None = None) → ttnn.Tensor

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

\[\mathrm{{output\_tensor}} = \mathrm{{input\_tensor\_a\ + input\_tensor\_b\ * \alpha}}\]
Parameters:

  • input_tensor_a (ttnn.Tensor) – the input tensor.

  • input_tensor_b (ttnn.Tensor) – the input tensor.

  • alpha (float) – the value to be multiplied.

Keyword Arguments:

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)
>>> alpha = 1.0
>>> output = ttnn.addalpha(tensor1, tensor2, alpha)