kijai 56b5dbbf82 Add different RMSNorm functions for testing ...

Initial testing for me shows that the RMSNorm from flash_attn.ops.triton.layer_norm is ~8-10% faster, apex is untested as I don't currently have it installed.

2024-11-04 14:11:58 +02:00

..

__init__.py

initial commit

2024-10-23 15:34:22 +03:00

asymm_models_joint.py

Add different RMSNorm functions for testing

2024-11-04 14:11:58 +02:00

layers.py

cleanup and align more to comfy code, switch to using cpu seed as well

2024-11-03 18:36:23 +02:00

mod_rmsnorm.py

tweak

2024-10-25 20:04:01 +03:00

residual_tanh_gated_rmsnorm.py

initial commit

2024-10-23 15:34:22 +03:00

rope_mixed.py

cleanup and align more to comfy code, switch to using cpu seed as well

2024-11-03 18:36:23 +02:00

temporal_rope.py

support cublas_ops with GGUF

2024-10-26 16:42:25 +03:00

utils.py

cleanup and align more to comfy code, switch to using cpu seed as well

2024-11-03 18:36:23 +02:00