Jaret Burkett 7602e476eb Exclude sensative layers from quantization in krea

2026-07-13 10:14:53 -06:00

..

src

Added reference token attention isolation (kv_cache) for Krea2 edit training. Same training cost with significant inference speed up. 2x inference speedup.

2026-07-09 12:00:55 -06:00

__init__.py

Add support for Krea2 (#906)

2026-06-23 09:18:14 -06:00

krea2.py

Exclude sensative layers from quantization in krea

2026-07-13 10:14:53 -06:00