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

concat_shape

def concat_shape[input_origin: ImmutOrigin, InputLayoutType: TensorLayout, //, input_type: DType](input_bufs: List[TileTensor[input_type, InputLayoutType, input_origin]], axis: Int) -> IndexList[InputLayoutType.rank]

Compute the output shape of a pad operation, and assert the inputs are compatible.

Parameters:

input_origin (ImmutOrigin): Origin of the input tensor.
InputLayoutType (TensorLayout): Layout type of the input tensor.
input_type (DType): Type of the input tensor.

Args:

input_bufs (List[TileTensor[input_type, InputLayoutType, input_origin]]): The input tensors list.
axis (Int): The axis.

Returns:

IndexList[InputLayoutType.rank]: The output shape.