cuda.core.experimental.GraphCompleteOptions

class cuda.core.experimental.GraphCompleteOptions(auto_free_on_launch: bool = False, upload_stream: Stream | None = None, device_launch: bool = False, use_node_priority: bool = False)

Customizable options for _graph.GraphBuilder.complete()

auto_free_on_launch

Automatically free memory allocated in a graph before relaunching. (Default to False)

Type:

bool, optional

upload_stream

Stream to use to automatically upload the graph after completion. (Default to None)

Type:

Stream, optional

device_launch

Configure the graph to be launchable from the device. This flag can only be used on platforms which support unified addressing. This flag cannot be used in conjunction with auto_free_on_launch. (Default to False)

Type:

bool, optional

use_node_priority

Run the graph using the per-node priority attributes rather than the priority of the stream it is launched into. (Default to False)

Type:

bool, optional