C++ segfault when passing callable kernel to another kernel from library

Take the following files

// lib.h 
#include "cudaq.h"

void kernel(cudaq::qvector<>& q);

// lib.cpp 
#include "lib.h"

__qpu__ void kernel(cudaq::qvector<>& q) {
    x(q[0]);
}

and

// user.cpp
#include "lib.h"

__qpu__ void userKernel(const std::function<void(cudaq::qvector<> &)> &init) {
  cudaq::qvector q(2);
  init(q);
}

int main() { userKernel(kernel); }

Compile and link with the following

nvq++ --enable-mlir -fPIC -c lib.cpp -o lib.o
nvq++ --enable-mlir -fPIC lib.o user.cpp 
# The run 
CUDAQ_LOG_LEVEL=info ./a.out 

This results in a segmentation fault.

Can anyone else reproduce this? I would be very thankful for anyone's help on this one. This kind of pattern will be a primary feature of future downstream libraries.

Another variation would be this

// lib.h 
#include "cudaq.h"

std::function<void(cudaq::qvector<>&)> get_kernel();//cudaq::qvector<>& q);

// lib.cpp
#include "lib.h"

__qpu__ void kernel(cudaq::qvector<> &q) { x(q[0]); }

std::function<void(cudaq::qvector<> &)> get_kernel() { return kernel; }

#include "lib.h"

__qpu__ void userKernel(const std::function<void(cudaq::qvector<> &)> &init) {
  cudaq::qvector q(2);
  init(q);
}

int main() { userKernel(get_kernel()); }