Support of batch processing?

'Cannot copy out of meta tensor; no data! Please use torch.nn.Module.to_empty() instead of torch.nn.Module.to() when moving module from meta to a different device.'

i got this error when doing manual batch processing(using asyncio.gather)

there is a batch processing and multidocument processing in docling

https://docling-project.github.io/docling/examples/batch_convert/
https://docling-project.github.io/docling/examples/run_with_formats/

it will help me so much if this were integrated!