Ling Xinnan

Looking forward to this update or is there any other way to achieve this?

> Dear @YH-Zheng, > > Thank you for your interest in rapids_singlecell. I want to support 64bit indptr in rsc. However there is currently a limitation with cupy when it...

> @YH-Zheng @SNOL2 We started working on multi-GPU support with dask. It's still in early development but the performance looks really promising. Great! Thanks for the updating.

I modified the code according to your suggestion, replacing ``` elif issparse(X): if X.has_canonical_format or not require_cf: return True else: X.sort_indices() X.sum_duplicates( ``` with ``` elif issparse(X): if not require_cf:...

The rsc version is 0.10.2 I used the pbmc3k dataset from sc.datasets.pbmc3k_processed(). ``` >>> adata AnnData object with n_obs × n_vars = 2638 × 13714 obs: 'n_genes', 'percent_mito', 'n_counts', 'louvain'...

> ### Description of feature > Blocked by [owkin/PyDESeq2#213](https://github.com/owkin/PyDESeq2/issues/213) > > See also https://github.com/theislab/pertpy/blob/2cc7ff77695cb616bb3ab207b5e506c0880aadb1/pertpy/tools/_differential_gene_expression/_pydeseq2.py#L62-L69 > > Migrated from [scverse/multi-condition-comparisions#13](https://github.com/scverse/multi-condition-comparisions/issues/13) Critical feature! Looking forward to it.

Fine. Thanks for your answer!

The issue remains when set init_pos = 'random'

> There will be a further update with rapids-24.10. I hope this will completely eliminate the problem. Thanks for your quick reply!

> There will be a further update with rapids-24.10. I hope this will completely eliminate the problem. Hi, have this be updated?