psychedelicious c7562dd6c0 fix(backend): mps should not use non_blocking ... We can get black outputs when moving tensors from CPU to MPS. It appears MPS to CPU is fine. See: - https://github.com/pytorch/pytorch/issues/107455 - https://discuss.pytorch.org/t/should-we-set-non-blocking-to-true/38234/28 Changes: - Add properties for each device on `TorchDevice` as a convenience. - Add `get_non_blocking` static method on `TorchDevice`. This utility takes a torch device and returns the flag to be used for non_blocking when moving a tensor to the device provided. - Update model patching and caching APIs to use this new utility. Fixes: #6545		2024-06-27 19:15:23 +10:00
..
convert_cache	make download and convert cache keys safe for filename length	2024-04-28 12:24:36 -04:00
model_cache	fix(backend): mps should not use non_blocking	2024-06-27 19:15:23 +10:00
model_loaders	[MM] Add support for probing and loading SDXL VAE checkpoint files (#6524)	2024-06-20 02:57:27 +00:00
__init__.py	add support for generic loading of diffusers directories	2024-06-07 13:54:30 +10:00
load_base.py	Merge remote-tracking branch 'origin/main' into lstein/feat/simple-mm2-api	2024-06-07 14:23:41 +10:00
load_default.py	make download and convert cache keys safe for filename length	2024-04-28 12:24:36 -04:00
memory_snapshot.py	final tidying before marking PR as ready for review	2024-03-01 10:42:33 +11:00
model_loader_registry.py	Experiment with using absolute paths within model management	2024-03-08 15:36:14 -05:00
model_util.py	make model manager v2 ready for PR review	2024-03-01 10:42:33 +11:00
optimizations.py	final tidying before marking PR as ready for review	2024-03-01 10:42:33 +11:00