FeepingCreature 7aceb9f91c Add --use-flash-attention flag. (#7223) ...

* Add --use-flash-attention flag.
This is useful on AMD systems, as FA builds are still 10% faster than Pytorch cross-attention.

2025-03-14 03:22:41 -04:00

..

diffusionmodules

Disable pytorch attention in VAE for AMD.

2025-02-14 05:42:14 -05:00

distributions

Small optimizations.

2024-12-18 18:23:28 -05:00

encoders

Make unclip more deterministic.

2024-01-14 17:28:31 -05:00

attention.py

Add --use-flash-attention flag. (#7223)

2025-03-14 03:22:41 -04:00

ema.py

Initial commit.

2023-01-16 22:37:14 -05:00

sub_quadratic_attention.py

Fix and enforce all ruff W rules.

2025-01-01 03:08:33 -05:00

temporal_ae.py

Basic Hunyuan Video model support.

2024-12-16 19:35:40 -05:00