An optimized solution to run HoverNet on patholgy WSI

Is your feature request related to a problem? Please describe.
I am trying to use a trained model in HoverNet to infer many SVS whole slide images. I followed every thing in tutorial, except changing PILReader to WSIReader: like
https://github.com/Project-MONAI/tutorials/blob/6be932f821c9ce4e795748dde7574beea8f8ea2c/pathology/hovernet/inference.py#L69

LoadImaged(keys="image", reader=WSIReader, backend="cucim", level=0)

I have tried the backend as either cucim or tifffile. But both cannot do the job quickly. It is more than 4 hours (not finished yet) in a single WSI. This will make the tool unfeasible for use. Also cucim gives "cuda out of memory" on multi-gpu.

Describe the solution you'd like
I think the limiting step here has something to do with post-processing after inference. There must be a way multi-thread that using something like dask.

CC: @KumoLiu might help triage the problem?!

Update:
All the runs with either cucim or tifffile stopped after about 5 hours with "cuda out of memory" error

Start with pathology/hovernet/inference.py and the linked tutorial, comparing the PILReader example with the WSIReader configuration using cucim or tifffile. Profile inference and post-processing on a representative SVS whole-slide image; done means processing is substantially faster and avoids the reported CUDA out-of-memory failures.