ttnn.addalpha_bw

ttnn.addalpha_bw(grad_tensor: ttnn.Tensor, input_tensor_a: ttnn.Tensor, input_tensor_b: ttnn.Tensor, alpha: float = 1, *, are_required_outputs: List[bool] = [True, True], memory_config: ttnn.MemoryConfig = None, input_grad: ttnn.Tensor = None, other_grad: ttnn.Tensor = None) → List of ttnn.Tensor

Performs backward operations for addalpha on input_tensor_b , input_tensor_a and alpha with given grad_tensor.

Parameters:

  • grad_tensor (ttnn.Tensor) – the input gradient tensor.

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

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

  • alpha (float) – Alpha value. Defaults to 1.

Keyword Arguments:

  • are_required_outputs (List[bool], optional) – List of required outputs. Defaults to [True, True].

  • memory_config (ttnn.MemoryConfig, optional) – Memory configuration for the operation. Defaults to None.

  • input_grad (ttnn.Tensor, optional) – Preallocated output tensor for gradient of input_tensor_a. Defaults to None.

  • other_grad (ttnn.Tensor, optional) – Preallocated output tensor for gradient of input_tensor_b. Defaults to None.

Returns:

List of ttnn.Tensor – the output tensor.

Note

Supported dtypes, layouts, and ranks:

Dtypes

Layouts

Ranks

BFLOAT16, BFLOAT8_B

TILE

2, 3, 4

bfloat8_b/bfloat4_b is only supported on TILE_LAYOUT

Example

# Create gradient and input tensors for addalpha backward
grad_tensor = ttnn.from_torch(
    torch.tensor([[1, 2], [3, 4]], dtype=torch.bfloat16), layout=ttnn.TILE_LAYOUT, device=device
)
tensor1 = ttnn.from_torch(
    torch.tensor([[1, 2], [3, 4]], dtype=torch.bfloat16, requires_grad=True), layout=ttnn.TILE_LAYOUT, device=device
)
tensor2 = ttnn.from_torch(
    torch.tensor([[1, 2], [3, 4]], dtype=torch.bfloat16, requires_grad=True), layout=ttnn.TILE_LAYOUT, device=device
)
alpha = 1.0

# Compute gradients for addalpha operation
output = ttnn.addalpha_bw(grad_tensor, tensor1, tensor2, alpha)
logger.info(f"Addalpha backward result: {output}")