dpctl.tensor.asarray([float("nan"), -1, 1], dtype="i8") doesn't raise ValueError like numpy

[densmirn]

Reproducer:

In [1]: import dpctl.tensor as dpt

In [2]: dpt.asarray([float("nan"), -1, 1], dtype="i8")
Out[2]: <dpctl.tensor._usmarray.usm_ndarray at 0x7fbc3ce8feb0>

In [3]: import numpy

In [4]: numpy.asarray([float('nan'), -1, 1], dtype="i8")
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-4-3fbb0a5af773> in <module>
----> 1 numpy.asarray([float('nan'), -1, 1], dtype="i8")

ValueError: cannot convert float NaN to integer

dpctl version:

In [5]: import dpctl

In [6]: dpctl.__version__
Out[6]: '0.11.0+31.gd9cfb43a'