Jaret Burkett 88360c68b2 Speed up MOSS-Image edit kv_cache training: reference isolation as unmasked flash attention instead of a boolean mask

2026-10-17 12:10:31 -06:00

..

src

Speed up MOSS-Image edit kv_cache training: reference isolation as unmasked flash attention instead of a boolean mask

2026-10-17 12:10:31 -06:00

__init__.py

Add support for MOSS Image

2026-10-16 08:09:45 -06:00

moss_image.py

Save qkv lora weights for MOSS Image as unfused LoRA, so they are more compatable with both fused and unfused weights.

2026-10-17 09:55:04 -06:00