ttnn.polygamma_bw

ttnn.polygamma_bw(grad_tensor: ttnn.Tensor, input_tensor: ttnn.Tensor, n: float, *, memory_config: ttnn.MemoryConfig = None) → List of ttnn.Tensor

Performs backward operations for polygamma on input_tensor, scalar with given grad_tensor.

\[\mathrm{{output\_tensor}}_i = \verb|polygamma_bw|(\mathrm{{grad\_tensor}}_i, \mathrm{{input\_tensor}}_i, \verb|n|)\]

Parameters:

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

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

• n (float) – Order of polygamma function.

Keyword Arguments:

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

Returns:

List of ttnn.Tensor – the output tensor.

Note

Supported dtypes, layouts, and ranks:

Dtypes	Layouts	Ranks
BFLOAT16	TILE	2, 3, 4

Example

# Create sample tensors for backward polygamma operation
grad_tensor = ttnn.from_torch(
    torch.tensor([[1, 2], [3, 4]], dtype=torch.bfloat16), layout=ttnn.TILE_LAYOUT, device=device
)
input_tensor = ttnn.from_torch(
    torch.tensor([[1, 2], [3, 4]], dtype=torch.bfloat16, requires_grad=True), layout=ttnn.TILE_LAYOUT, device=device
)
n = 1

# Call the polygamma_bw function
output = ttnn.polygamma_bw(grad_tensor, input_tensor, n)
logger.info(f"Polygamma Backward: {output}")