ttnn.cumprod

ttnn.cumprod(input: ttnn.Tensor, dim: int, *, dtype: ttnn.DataType | None, reverse_order: bool, optional, default False, out: ttnn.Tensor | None) → ttnn.Tensor

Returns cumulative product of input along dimension dim For a given input of size N, the output will also contain N elements and be such that:

\[\mathrm{{output}}_i = \mathrm{{input}}_1 \times \mathrm{{input}}_2 \times \cdots \times \mathrm{{input}}_i\]

Parameters:

input (ttnn.Tensor) – input tensor. Must be on the device.
dim (int) – dimension along which to compute cumulative product

Keyword Arguments:

dtype (ttnn.DataType, optional) – desired output type. If specified then input tensor will be casted to dtype before processing.
reverse_order (bool, optional, default False) – whether to perform accumulation from the end to the beginning of accumulation axis.
out (ttnn.Tensor, optional) – preallocated output. If specified, out must have same shape as input, and must be on the same device.

Returns:

ttnn.Tensor – the output tensor.

Note

If both dtype and output are specified then output.dtype must match dtype.

Supported dtypes, layout, ranks and dim values:

Dtypes	Layouts	Ranks	dim
BFLOAT16, FLOAT32	TILE	1, 2, 3, 4, 5	-rank <= dim < rank
INT32, UINT32	TILE	3, 4, 5	dim in {0, 1, …, rank - 3} or dim in {-rank, -rank + 1, …, -3}

Memory Support:

Interleaved: DRAM and L1

Limitations:

Preallocated output must have the same shape as the input
Preallocated output for integer types is not supported

Example

# Create tensor
tensor_input = ttnn.rand((2, 3, 4), device=device)

# Apply ttnn.cumprod() on dim=0
tensor_output = ttnn.cumprod(tensor_input, dim=0)
logger.info(f"Cumprod result: {tensor_output}")

# With preallocated output and dtype
preallocated_output = ttnn.rand([2, 3, 4], dtype=ttnn.bfloat16, device=device)

# Apply ttnn.cumprod() with out and dtype
tensor_output = ttnn.cumprod(tensor_input, dim=0, dtype=ttnn.bfloat16, out=preallocated_output)
logger.info(f"Cumprod with preallocated output result: {tensor_output}")