ttnn.fill_implicit_tile_padding

ttnn.fill_implicit_tile_padding(input_tensor: ttnn.tensor, *, memory_config: ttnn.MemoryConfig = None) → ttnn.Tensor

Fills the implicit padding of a tiled input tensor with the specified value. Specifically, any nD tensor will have the implicit padding of the last 2 dims that exists from [height:tile_height, width:tile_width] filled with the specified value.

Argument | Description		Data type	Valid range	Required
input_tensor | A tiled input tensor		tt_lib.tensor.Tensor		Yes
fill_value | value to fill into padding		float	[-inf , inf]	Yes

Parameters:

• input_tensor (ttnn.tensor) – Any input tensor with desired device and data types for output tensor.

• fill_value (value greater than 0) – Value to fill the tensor padding with.

Keyword Arguments:

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

Returns:

ttnn.Tensor – the output tensor.