Harmony update (#353)

* first iteration

* update categories

* add kernel for outer

* add use_gemm

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* add kernels

* remove atomics

* Update src/rapids_singlecell/preprocessing/_harmony/__init__.py

Co-authored-by: Michelle Gill <1757241+mlgill@users.noreply.github.com>

* Update src/rapids_singlecell/preprocessing/_harmony_integrate.py

Co-authored-by: Michelle Gill <1757241+mlgill@users.noreply.github.com>

* add more kernels

* add release note

* remove print

* add test

* add reduction for entropy

* reduce memory

* update typing

* update defaults

* update scatter with bias vector access

* first clean up

* add release notes for 0.12.4

* add possibilty to have theta as a list or array

* remove print

* enforce C-Cont

* release notes for theta

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Michelle Gill <1757241+mlgill@users.noreply.github.com>

Author: 3 people

docs/release-notes/0.12.4.md

@@ -2,11 +2,13 @@
 
 ```{rubric} Features
 ```
+* `theta` in `pp.harmony_integrate` can now be a list or array {pr}`353` {smaller}`S Dicks`
 
 ```{rubric} Performance
 ```
 * replace `adata._sanitize` for `pp.highly_variable_genes`. Now only `batch_key` column will be categorized {pr}`355` {smaller}`S Dicks`
 * replace `adata._sanitize` for `tl.embedding_density`. Now only `groupby` column will be categorized {pr}`355` {smaller}`S Dicks`
+* Refactored `pp.harmony_integrate` to be more memory efficient and faster. {pr}`353` {smaller}`S Dicks`
 
 ```{rubric} Bug fixes
 ```

docs/release-notes/index.md

@@ -3,6 +3,8 @@
 # Release notes
 
 ## Version 0.12.0
+```{include} /release-notes/0.12.4.md
+```
 ```{include} /release-notes/0.12.3.md
 ```
 ```{include} /release-notes/0.12.2.md