Surya Narayanan Hari

This could be out of my depth, but just to start a discussion, we could replicate this behavior [big_future = client.scatter(tile)](https://github.com/Dana-Farber-AIOS/pathml/blob/b2eca9ed02e990ace16f3cb7f23b16828e12cc19/pathml/core/slide_data.py#L331) at the slide level, in `slide_dataset.run ` https://github.com/Dana-Farber-AIOS/pathml/blob/b2eca9ed02e990ace16f3cb7f23b16828e12cc19/pathml/core/slide_dataset.py#L56 where...

Yes, that makes sense. I'm happy to take this up.

This issue still persists, `WARNING - Unmanaged memory use is high. This may indicate a memory leak or the memory may not be released to the OS; see https://distributed.dask.org/en/latest/worker.html#memtrim for...

While I look at the diagnostics dashboard, I wanted to tell you this- a smaller tile size (I think) didn't kill my program, but took about 8 hours to run...

So I'm looking at it right now, and all memory seems to be un-managed. It seems that one needs to be calling `.free()` or doing garbage collection on this, and...

`MALLOC_TRIM_THRESHOLD_=0` did not fix it. 

not using gpu, since I need cudnn==8.1.x. I'm still sorting that out now. Do you have any knowledge of how to install cudnn 8.1.x? I have a machine with cuda...

Btw, with `distributed=False`, I am able to get it work, but it might take over 4.5 hours per slide. Do you have any ideas on how to leverage the fact...

This is out of my paygrade folks, Idk enough about dask distributed to comment helpfully. I leave it to you.

Hi, I am trying to find whether I can get tiles at different magnifications from my H&E WSI. Searching for magnification in the docs, was not successful. Is this PR...