github/ai-toolkit
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

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

Browse Source
This commit is contained in:
Jaret Burkett
2026-07-09 12:00:55 -06:00
parent 6233efe1bb
commit a4bbe167ce
7 changed files with 177 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
version.py
View File

@@ -1 +1 @@
VERSION = "0.10.21"
VERSION = "0.10.22"