comfyanonymous 96d891cb94 Speedup on some models by not upcasting bfloat16 to float32 on mac.		2025-02-24 05:41:32 -05:00
..
diffusionmodules	Disable pytorch attention in VAE for AMD.	2025-02-14 05:42:14 -05:00
distributions	…
encoders	…
attention.py	Speedup on some models by not upcasting bfloat16 to float32 on mac.	2025-02-24 05:41:32 -05:00
ema.py	…
sub_quadratic_attention.py	…
temporal_ae.py	…