ttnn.triu

ttnn.triu(input_tensor: ttnn.Tensor, *, diagonal: float = 0, memory_config: ttnn.MemoryConfig = None) → ttnn.Tensor

Performs triu function on input_tensor, diagonal.

\[\mathrm{{output\_tensor}}_i = \verb|triu|(\mathrm{{input\_tensor}}_i, \verb|diagonal|)\]

Parameters:

input_tensor (ttnn.Tensor) – the input tensor.

Keyword Arguments:

• diagonal (float) – diagonal value. Defaults to 0.

• 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

# Create a tensor with random values
tensor = ttnn.rand([2, 2], dtype=ttnn.bfloat16, layout=ttnn.TILE_LAYOUT, device=device)

# Extract upper triangular part
output = ttnn.triu(tensor, diagonal=0)
logger.info(f"Upper triangular: {output}")