cuda.bindings._v2.driver.MemCpyFlags#

class cuda.bindings._v2.driver.MemCpyFlags(value: int)#

Flags to specify for copies within a batch. For more details see cuMemcpyBatchAsync.

See CUmemcpyFlags.

DEFAULT: 0

PREFER_OVERLAP_WITH_COMPUTE: 1

Hint to the driver to try and overlap the copy with compute work on the SMs.