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.

Parameters:: ind_ex (unsigned int) – The ind_ex of the target GPU, >= 0 and < accessibleDevices.
Returns:: Reference in which to return the device handle.
Return type:: intptr_t