Added propagate copy_xj CUDA sparse support using matrix mul

Author: dferre97

GNNlib/ext/GNNlibCUDAExt.jl

@@ -7,14 +7,6 @@ using GNNGraphs: GNNGraph, COO_T, SPARSE_T
 
 ###### PROPAGATE SPECIALIZATIONS ####################
 
-## COPY_XJ 
-
-## avoid the fast path on gpu until we have better cuda support
-function GNNlib.propagate(::typeof(copy_xj), g::GNNGraph{<:Union{COO_T, SPARSE_T}}, ::typeof(+),
-        xi, xj::AnyCuMatrix, e)
-    propagate((xi, xj, e) -> copy_xj(xi, xj, e), g, +, xi, xj, e)
-end
-
 ## E_MUL_XJ 
 
 ## avoid the fast path on gpu until we have better cuda support

GNNlib/src/msgpass.jl

@@ -213,7 +213,7 @@ end
 ## COPY_XJ 
 
 function propagate(::typeof(copy_xj), g::GNNGraph, ::typeof(+), xi, xj::AbstractMatrix, e)
-    A = adjacency_matrix(g, weighted = false)
+    A = adjacency_matrix(g, eltype(xj); weighted = false)
     return xj * A
 end