warp.get_mempool_release_threshold#

warp.get_mempool_release_threshold(device=None)[source]#

Get the CUDA memory pool release threshold on the device.

Parameters:

device (Device | str | None) – The Device or device identifier for which the query is to be performed. If None, the default device will be used.

Returns:

The memory pool release threshold in bytes.

Raises:

  • ValueError – If device is not a CUDA device.

  • RuntimeError – If device is a CUDA device, but does not support memory pools.

Return type:

int