Yao Matrix aa541b9fab make KandinskyV22PipelineInpaintCombinedFastTests::test_float16_inference pass on XPU (#11308) ...

loose expected_max_diff from 5e-1 to 8e-1 to make
KandinskyV22PipelineInpaintCombinedFastTests::test_float16_inference
pass on XPU

Signed-off-by: Matrix Yao <matrix.yao@intel.com>

2025-04-14 07:49:20 +01:00

..

fixtures

Comprehensive type checking for from_pretrained kwargs (#10758)

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

hooks

Update Ruff to latest Version (#10919)

2025-04-09 16:51:34 +05:30

lora

[Tests] Cleanup lora tests utils (#11276)

2025-04-10 15:50:34 +05:30

models

Update Ruff to latest Version (#10919)

2025-04-09 16:51:34 +05:30

others

fix consisid imports (#11254)

2025-04-09 18:49:32 +05:30

pipelines

make KandinskyV22PipelineInpaintCombinedFastTests::test_float16_inference pass on XPU (#11308)

2025-04-14 07:49:20 +01:00

quantization

[bistandbytes] improve replacement warnings for bnb (#11132)

2025-04-08 21:18:34 +05:30

remote

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

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

schedulers

Update Ruff to latest Version (#10919)

2025-04-09 16:51:34 +05:30

single_file

Update Ruff to latest Version (#10919)

2025-04-09 16:51:34 +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