Sayak Paul e8da75dff5 [bitsandbytes] allow directly CUDA placements of pipelines loaded with bnb components (#9840) ...

* allow device placement when using bnb quantization.

* warning.

* tests

* fixes

* docs.

* require accelerate version.

* remove print.

* revert to()

* tests

* fixes

* fix: missing AutoencoderKL lora adapter (#9807)

* fix: missing AutoencoderKL lora adapter

* fix

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* fixes

* fix condition test

* updates

* updates

* remove is_offloaded.

* fixes

* better

* empty

---------

Co-authored-by: Emmanuel Benazera <emmanuel.benazera@jolibrain.com>

2024-12-04 22:27:43 +05:30

..

fixtures

change to 2024 in the license (#6902)

2024-02-08 08:19:31 -10:00

lora

[Tests] skip nan lora tests on PyTorch 2.5.1 CPU. (#9975)

2024-11-22 12:45:21 +05:30

models

[tests] refactor vae tests (#9808)

2024-12-04 15:58:36 +05:30

others

Fixes EMAModel "from_pretrained" method (#9779)

2024-11-01 09:20:19 +05:30

pipelines

[tests] refactor vae tests (#9808)

2024-12-04 15:58:36 +05:30

quantization/bnb

[bitsandbytes] allow directly CUDA placements of pipelines loaded with bnb components (#9840)

2024-12-04 22:27:43 +05:30

schedulers

Fix beta and exponential sigmas + add tests (#9954)

2024-11-20 01:20:34 -10:00

single_file

make pipelines tests device-agnostic (part2) (#9400)

2024-11-29 11:33:41 +05:30

__init__.py

fix issues with loading, add test for pipeline

2022-06-07 15:40:36 +02:00

conftest.py

change to 2024 in the license (#6902)

2024-02-08 08:19:31 -10:00