Cupy arrays and scipy.stats random variables

Question

I have a problem with arrays created by CuPy and using them with SciPy.Stats random variables (such as the normal continuous random variable scipy.stats.norm). For example, I want to evaluate the density at a point x under different scale parameters (see the code below). If I pass a numpy array to the pdf method, everything works well. However, if I pass a cupy array to the method, it always returns the following error:

TypeError: Implicit conversion to a NumPy array is not allowed. Please use `.get()` to construct a NumPy array explicitly.

May I ask why it returns this error and if there is any way to fix it?

import cupy as cp
import numpy as np
from scipy.stats import norm

scale1 = np.arange(start=1, stop=11, step=1)
scale2 = cp.arange(start=1, stop=11, step=1)
rv1 = norm(loc=0, scale=scale1)
rv2 = norm(loc=0, scale=scale2)
x = 0
rv1.pdf(x)
rv2.pdf(x)