[QST]

[diego-s]

Hi all,
I have a question on the sparse matrix non-zero entry limit:
"Limit note: For GPU-backed AnnData, the upper limit is governed by the sparse matrix .nnz value of 2**31-1 (2,147,483,647). This is due to the maximum indptr size currently supported by cupy for sparse matrices."
Does this mean rapids single-cell cannot be used with datasets with more than this limit of non-zero entry values in the sparse matrix?
Thank you very much in advance,
Diego

[Intron7]

Hey you can use it for more than this. But you need to use dask