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

as_dynamic_row_major_1d

def as_dynamic_row_major_1d[dtype: DType](tensor: LayoutTensor[dtype, element_layout=tensor.element_layout, layout_int_type=tensor.layout_int_type, linear_idx_type=tensor.linear_idx_type, masked=tensor.masked, alignment=tensor.alignment]) -> LayoutTensor[dtype, Layout.row_major(Int(-1)), ImmutAnyOrigin]

Reinterprets a generic-address LayoutTensor as a 1-D dynamic row-major tensor.

The pointer and total element count are preserved; the result has an unknown-value row-major layout so it can be passed to routines that require a 1-D runtime-layout tensor without copying data.

Parameters:

dtype (DType): The element data type of the input tensor.

Args:

tensor (LayoutTensor[dtype, element_layout=tensor.element_layout, layout_int_type=tensor.layout_int_type, linear_idx_type=tensor.linear_idx_type, masked=tensor.masked, alignment=tensor.alignment]): The immutable generic-address tensor to reinterpret.

Returns:

LayoutTensor[dtype, Layout.row_major(Int(-1)), ImmutAnyOrigin]: A 1-D LayoutTensor with a row_major(UNKNOWN_VALUE) layout backed by the same storage as tensor.