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
advanced_indexing_getitem_shape_fn
def advanced_indexing_getitem_shape_fn[Indices: TypeList[Indices.values], //, start_axis: Int](input_tensor: T, indices: TensorTuple[*Indices.values]) -> IndexList[(Int((add T.rank, Indices.values[0].rank)) - Int(len(Indices.values)))]
Computes the output shape for the advanced_indexing_getitem graph op.
Returns:
IndexList[(Int((add T.rank, Indices.values[0].rank)) - Int(len(Indices.values)))]