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

slice_dim_as_view

def slice_dim_as_view[dtype: DType, dim: Int](tensor: TileTensor[dtype, Storage=tensor.Storage, address_space=tensor.address_space, linear_idx_type=tensor.linear_idx_type], start: Int, end: Int, step: Int) -> TileTensor[dtype, Layout[*?, *?], tensor.origin, address_space=tensor.address_space]

Returns a view of tensor sliced along a single dimension.

The returned view shares the underlying data with tensor but adjusts the offset, stride, and extent of dim to reflect the normalized start, end, and step range.

Args:

tensor (TileTensor[dtype, Storage=tensor.Storage, address_space=tensor.address_space, linear_idx_type=tensor.linear_idx_type]): Source tensor to slice.
start (Int): Starting index along dim (negative values wrap from the end).
end (Int): Stopping index along dim (exclusive; negative values wrap from the end).
step (Int): Stride between selected indices along dim; must be non-zero.

Returns:

TileTensor[dtype, Layout[*?, *?], tensor.origin, address_space=tensor.address_space]