Commit e301bfc
committed
Update base for Update on "[Executorch][llm] Enable local global attention in export_llama script"
Added a new option of --local_global_attention that takes in pattern of sizes to determine which layers are using local sliding window attention.
For example, [0, 256, 256, 0, 256, 256] can be used for 6 layers transformer. Or you can also use [0, 256, 256] as pattern you want
to repeat.
Differential Revision: [D73891423](https://our.internmc.facebook.com/intern/diff/D73891423/)
cc larryliu0820 mergennachin cccclai helunwencser jackzhxng
[ghstack-poisoned]1 parent d933b87 commit e301bfc
File tree
0 file changed
+0
-0
lines changed0 file changed
+0
-0
lines changed
0 commit comments