Add patch to pybind11 to work around pybind/pybind11#4606

with CUDA12

patches/pybind11-cuda12.patch

@@ -0,0 +1,15 @@
+diff --git a/include/pybind11/cast.h b/include/pybind11/cast.h
+index 3a404602..9054478c 100644
+--- a/include/pybind11/cast.h
++++ b/include/pybind11/cast.h
+@@ -42,7 +42,9 @@ using make_caster = type_caster<intrinsic_t<type>>;
+ // Shortcut for calling a caster's `cast_op_type` cast operator for casting a type_caster to a T
+ template <typename T>
+ typename make_caster<T>::template cast_op_type<T> cast_op(make_caster<T> &caster) {
+-    return caster.operator typename make_caster<T>::template cast_op_type<T>();
++    // https://github.com/pybind/pybind11/issues/4606 with CUDA 12
++    //return caster.operator typename make_caster<T>::template cast_op_type<T>();
++    return caster;
+ }
+ template <typename T>
+ typename make_caster<T>::template cast_op_type<typename std::add_rvalue_reference<T>::type>