Mojo function
scatter_nd
scatter_nd[output_type: DType, indices_type: DType, single_thread_blocking_override: Bool, target: StringSlice[StaticConstantOrigin] = "cpu"](data: TileTensor[output_type, LayoutType, origin, linear_idx_type=linear_idx_type, element_shape_types=element_shape_types], indices: TileTensor[indices_type, LayoutType, origin, linear_idx_type=linear_idx_type, element_shape_types=element_shape_types], updates: TileTensor[output_type, LayoutType, origin, linear_idx_type=linear_idx_type, element_shape_types=element_shape_types], output: TileTensor[output_type, LayoutType, origin, linear_idx_type=linear_idx_type, element_shape_types=element_shape_types], context: DeviceContextPtr = DeviceContextPtr())
Scatter_nd operation without any reduction.
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!