cuda.bindings.nvml.GpuInstancePlacement#

class cuda.bindings.nvml.GpuInstancePlacement(size=1)#

Empty-initialize an array of nvmlGpuInstancePlacement_t.

The resulting object is of length size and of dtype gpu_instance_placement_dtype. If default-constructed, the instance represents a single struct.

Parameters:

size (int) – number of structs, default=1.

See also

nvmlGpuInstancePlacement_t

__init__(*args, **kwargs)#

Methods

__init__(*args, **kwargs)

from_buffer(buffer)

Create an GpuInstancePlacement instance with the memory from the given buffer.

from_data(data)

Create an GpuInstancePlacement instance wrapping the given NumPy array.

from_ptr(intptr_t ptr, size_t size=1, ...)

Create an GpuInstancePlacement instance wrapping the given pointer.

Attributes

ptr

Get the pointer address to the data as Python int.

size_

Union[~_numpy.uint32, int]:

start

Union[~_numpy.uint32, int]: