cuda.bindings.nvml.device_get_handle_by_index_v2

cuda.bindings.nvml.device_get_handle_by_index_v2(unsigned int ind_ex) → intptr_t

Acquire the handle for a particular device, based on its ind_ex.

:param ind_ex: The ind_ex of the target GPU, >= 0 and < ``accessibleDevices``.
:type ind_ex: unsigned int

:returns: Reference in which to return the device handle.
:rtype: intptr_t

.. seealso:: `nvmlDeviceGetHandleByIndex_v2`