pylibcugraphops.operators.agg_concat_n2n_e2n_fwd = <nanobind.nb_func object>#
Computes the forward pass for both a simple aggregation using node features in an

node-to-node reduction (n2n) and a simple aggregation using edge features in an edge-to-node reduction (e2n) on a graph where the results are concatenated. Moreover, the original features of output nodes are concatenated at the end (agg_concat).

    output_embedding: device array, input_node_embedding: device array,
    input_edge_embedding: device array, graph: pylibcugraphops.csc_int[32|64],
    dim_node: int, dim_edge: int,
    aggregation_operation: pylibcugraphops.operators.AggOp = pylibcugraphops.operators.AggOp.Sum,
    output_extrema_location: Optional[device array] = None, stream_id: int = 0
) -> None
output_embeddingdevice array type

Device array containing the output node embeddings. Shape: (graph.n_dst_nodes, dim_node + dim_edge + dim_node).

input_node_embeddingdevice array type

Device array containing the input node embeddings. Shape: (graph.n_dst_nodes, dim_node).

input_edge_embeddingdevice array type

Device array containing the input edge embeddings. Shape: (n_edges, dim_edge).

graphopaque graph type

The graph used for the operation.


Node feature dimensionality.


Edge Feature dimensionality.

aggregation_operationAggOp, default=AggOp.Sum

The kind of aggregation operation.

output_extrema_locationdevice array type | None

Device array containing the location of the min/max embeddings. This is required for min/max aggregation only, and can be None otherwise. Shape: (graph.n_dst_nodes, dim_node + dim_edge) if set.

stream_idint, default=0

CUDA stream pointer as a python int.