Added reference token attention isolation (kv_cache) for Krea2 edit training. Same training cost with significant inference speed up. 2x inference speedup.
This commit is contained in:
1 parent
6233efe1bb
commit
a4bbe167ce
7 files changed
+177
-13
No files matched your search
+1
-1
@@ -1 +1 @@
|
||||
VERSION = "0.10.21"
|
||||
VERSION = "0.10.22"
|
||||
Reference in new issue
Block a user