Decoder bounded CUDA memory is allocated by driver and the pool size is fixed. Since we don't know how many buffers would be held by downstream non-CUDA element, we should download such CUDA memory and release it back to decoder.
Due to an influx of spam, we have had to impose restrictions on new accounts. Please see this wiki page for instructions on how to get full permissions. Sorry for the inconvenience.
Decoder bounded CUDA memory is allocated by driver and the pool size is fixed. Since we don't know how many buffers would be held by downstream non-CUDA element, we should download such CUDA memory and release it back to decoder.