For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /get-started.md).

Mojo function

transpose

def transpose[dtype: DType, //](output: TileTensor[dtype, Storage=output.Storage, linear_idx_type=output.linear_idx_type], input: TileTensor[dtype, Storage=input.Storage, linear_idx_type=input.linear_idx_type], perms: Pointer[Int], ctx: Optional[DeviceContext] = None)

Permute the axis of input based on perms, and place the result in output.

Example:

transpose(output, input, [2, 0, 1])
# guarantees output[x, y, z] = input[z, x, y]

Parameters:

• ​dtype (DType): The dtype of buffer elements.

Args:

• ​output (TileTensor[dtype, Storage=output.Storage, linear_idx_type=output.linear_idx_type]): The output buffer.
• ​input (TileTensor[dtype, Storage=input.Storage, linear_idx_type=input.linear_idx_type]): The input buffer.
• ​perms (Pointer[Int]): Permutation of the input axes.
• ​ctx (Optional[DeviceContext]): The context to execute the work on.