I run the codes as follow:
y = np.array(arr)
kmeans = KMeans(n_clusters=10, init='k-means++',random_state=None).fit(y)
sample_silhouette_values = silhouette_samples(y, kmeans.labels_)

The "arr" in first line was a two-dimensional array that had 270,000 rows and 30 columns.
And I got error as follow:

Traceback (most recent call last):
File "D:\eclipse-neon64\workSpace\cluster-sklearn\cluster\cluster-sklearn.py", line 41, in <module>
sample_silhouette_values = silhouette_samples(y, kmeans.labels_)
File "D:\python\lib\site-packages\sklearn\metrics\cluster\unsupervised.py", line 168, in silhouette_samples
distances = pairwise_distances(X, metric=metric, **kwds)
File "D:\python\lib\site-packages\sklearn\metrics\pairwise.py", line 1240, in pairwise_distances
return _parallel_pairwise(X, Y, func, n_jobs, **kwds)
File "D:\python\lib\site-packages\sklearn\metrics\pairwise.py", line 1083, in _parallel_pairwise
return func(X, Y, **kwds)
File "D:\python\lib\site-packages\sklearn\metrics\pairwise.py", line 245, in euclidean_distances
distances = safe_sparse_dot(X, Y.T, dense_output=True)
File "D:\python\lib\site-packages\sklearn\utils\extmath.py", line 189, in safe_sparse_dot
return fast_dot(a, b)
ValueError: array is too big; arr.size * arr.dtype.itemsize is larger than the maximum possible size.

I don't think it is same as #4701 or #4197 ,but they have some similarity.