Pierre Chapuis 2796117d2d properly check for bfloat16 ... - we check only the test device, not the machine in general - we don't want emulated bfloat16 (e.g. CPU)		2024-10-09 11:20:27 +02:00
..
adapters	make sure adapters can access the context of their parent chain	2024-10-03 10:51:11 +02:00
e2e	add test_diffusion_std_random_init_bfloat16 e2e test	2024-10-03 11:05:09 +02:00
fluxion	switch pytest import mode to importlib	2024-06-24 17:19:05 +02:00
foundationals	modify some foundational tests to also test in float16 and bfloat16	2024-10-03 11:05:09 +02:00
training_utils	fix typing issues coming from torch 2.4 version ; typing is not guaranteed for torch < 2.4	2024-08-02 12:02:00 +02:00
__init__.py	initial commit	2023-08-04 15:28:41 +02:00
conftest.py	properly check for bfloat16	2024-10-09 11:20:27 +02:00
utils.py	ella adapter implementation. tested with sd1.5 model	2024-09-04 11:38:22 +02:00