Error in getgraph when graph is on gpu

Running the following script

using Flux
using GraphNeuralNetworks

n = m = d = N = 10

g = Flux.batch([rand_graph(n, m, ndata=rand(d, n)) for i in 1:N])
getgraph(g, 1)
getgraph(g |> gpu, 1)

results in the following error message for the last call:

LoadError: GPU compilation of kernel broadcast_kernel(CUDA.CuKernelContext, CUDA.CuDeviceVector{Bool, 1}, Base.Broadcast.Broadcasted{Nothing, Tuple{Base.OneTo{Int64}}, typeof(in), Tuple{Base.Broadcast.Extruded{CUDA.CuDeviceVector{Int64, 1}, Tuple{Bool}, Tuple{Int64}}, CUDA.CuRefValue{Vector{Int64}}}}, Int64) failed
KernelError: passing and using non-bitstype argument

Argument 4 to your kernel function is of type Base.Broadcast.Broadcasted{Nothing, Tuple{Base.OneTo{Int64}}, typeof(in), Tuple{Base.Broadcast.Extruded{CUDA.CuDeviceVector{Int64, 1}, Tuple{Bool}, Tuple{Int64}}, CUDA.CuRefValue{Vector{Int64}}}}, which is not isbits:
  .args is of type Tuple{Base.Broadcast.Extruded{CUDA.CuDeviceVector{Int64, 1}, Tuple{Bool}, Tuple{Int64}}, CUDA.CuRefValue{Vector{Int64}}} which is not isbits.
    .2 is of type CUDA.CuRefValue{Vector{Int64}} which is not isbits.
      .x is of type Vector{Int64} which is not isbits.

I am on Julia 1.7.2, Flux version 0.12.9 and GraphNeuralNetworks 0.3.14.
Edit: Also error with GNN 0.4.0 and Flux 0.13.0
Am I missing something?

Start by running the provided Julia script and compare getgraph(g, 1) with getgraph(g |> gpu, 1) using the reported package versions. Trace the getgraph entry point and the GPU broadcast shown in the error; done means the GPU call completes without the reported kernel compilation failure and existing behavior remains intact.