hlky a7d53a5939 Don't override torch_dtype and don't use when quantization_config is set (#11039) ...

* Don't use `torch_dtype` when `quantization_config` is set

* up

* djkajka

* Apply suggestions from code review

---------

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

2025-03-21 21:58:38 +05:30

..

fixtures

Comprehensive type checking for from_pretrained kwargs (#10758)

2025-02-22 13:15:19 +00:00

hooks

Module Group Offloading (#10503)

2025-02-14 12:59:45 +05:30

lora

[LoRA] change to warning from info when notifying the users about a LoRA no-op (#11044)

2025-03-12 21:20:48 +05:30

models

[tests] make cuda only tests device-agnostic (#11058)

2025-03-20 10:12:35 +00:00

others

[Utils] add utilities for checking if certain utilities are properly documented (#7763)

2025-02-20 12:37:00 +05:30

pipelines

Don't override torch_dtype and don't use when quantization_config is set (#11039)

2025-03-21 21:58:38 +05:30

quantization

[tests] enable bnb tests on xpu (#11001)

2025-03-19 16:33:11 +00:00

remote

[hybrid inference 🍯🐝] Add VAE encode (#11017)

2025-03-12 11:23:41 +00:00

schedulers

[tests] make cuda only tests device-agnostic (#11058)

2025-03-20 10:12:35 +00:00

single_file

[Single File] Add single file loading for SANA Transformer (#10947)

2025-03-10 08:38:30 +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