cuda.bindings.nvml.device_get_vgpu_capabilities#

cuda.bindings.nvml.device_get_vgpu_capabilities(
intptr_t device,
int capability,
) → unsigned int#

Retrieve the requested vGPU capability for GPU.

Refer to the nvmlDeviceVgpuCapability_t structure for the specific capabilities that can be queried. The return value in cap_result reports a non-zero value indicating that the capability is supported, and also reports the capability’s data based on the queried capability. For Maxwell ™️ or newer fully supported devices.

Parameters:

  • device (intptr_t) – The identifier of the target device.

  • capability (DeviceVgpuCapability) – Specifies the nvmlDeviceVgpuCapability_t to be queried.

Returns:

Specifies that the queried capability is supported,

and also returns capability’s data.

Return type:

unsigned int

See also

nvmlDeviceGetVgpuCapabilities