[BUG] AttributeError when using cuml.accel with PyOD KNN

[btepera]

Describe the bug
I am attempting to use cuML with PyOD to use KNN for outlier detection, following the code in this example script.

When I try to fit the KNN model, I get an attribute error for an attribute that does not exist in the cuML implementation:

%load_ext cuml.accel

from pyod.models.knn import KNN
from pyod.utils.data import generate_data
from pyod.utils.data import evaluate_print
from pyod.utils.example import visualize

contamination = 0.1  # percentage of outliers
n_train = 200000  # number of training points
n_test = 100000  # number of testing points

X_train, X_test, y_train, y_test = generate_data(
    n_train=n_train, n_test=n_test, contamination=contamination)

clf_name = 'KNN'
clf = KNN()
clf.fit(X_train)

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
Cell In[1], line 17
     15 clf_name = 'KNN'
     16 clf = KNN()
---> 17 clf.fit(X_train)

File [/raid/btepera/miniforge3/envs/rapids-25.04/lib/python3.12/site-packages/pyod/models/knn.py:197](http://127.0.0.1:8890/raid/btepera/miniforge3/envs/rapids-25.04/lib/python3.12/site-packages/pyod/models/knn.py#line=196), in KNN.fit(self, X, y)
    192 self.neigh_.fit(X)
    194 # In certain cases, _tree does not exist for NearestNeighbors
    195 # See Issue #158 (https://github.com/yzhao062/pyod/issues/158)
    196 # n_neighbors = 100
--> 197 if self.neigh_._tree is not None:
    198     self.tree_ = self.neigh_._tree
    200 else:

File base.pyx:865, in cuml.internals.base.UniversalBase.__getattr__()

File base.pyx:833, in cuml.internals.base.UniversalBase.__getattr__()

File base.pyx:388, in cuml.internals.base.Base.__getattr__()

AttributeError: _tree

Using these package versions:
cuml 25.4.0a168
scikit-learn 1.6.1
pyod 2.0.4