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

Mojo function

pad_repeat

def pad_repeat[dtype: DType, paddings_type: DType](output: TileTensor[dtype, Storage=output.Storage, address_space=output.address_space, linear_idx_type=output.linear_idx_type, element_size=output.element_size], input: TileTensor[dtype, Storage=input.Storage, address_space=input.address_space, linear_idx_type=input.linear_idx_type, element_size=input.element_size], paddings: UnsafePointer[Scalar[paddings_type]])

Fill output with values from input, and edges padded boundary values from the unpadded region.

Example: var input = [[1, 2], [3, 4]] var paddings = [2, 2, 1, 0]

Yields: output = [[1, 1, 2], [1, 1, 2], [1, 1, 2], [3, 3, 4], [3, 3, 4], [3, 3, 4]]

Parameters:

dtype (DType): DType of the input/output buffer.
paddings_type (DType): DType of the input, output, and padding buffers.

Args:

output (TileTensor[dtype, Storage=output.Storage, address_space=output.address_space, linear_idx_type=output.linear_idx_type, element_size=output.element_size]): The output buffer.
input (TileTensor[dtype, Storage=input.Storage, address_space=input.address_space, linear_idx_type=input.linear_idx_type, element_size=input.element_size]): The input buffer.
paddings (UnsafePointer[Scalar[paddings_type]]): Ordered (before, after) padding sizes for each axis.