Commit 0d30b1c
committed
Update base for Update on "[Executorch][llm] Add support for ring kv cache and ring attention"
Introduced CachePositionManager to keep track of what is the position for each slot in ring kv cache. This is used to generate mask.
Differential Revision: [D73891427](https://our.internmc.facebook.com/intern/diff/D73891427/)
[ghstack-poisoned]1 parent d1bc0e6 commit 0d30b1c
File tree
0 file changed
+0
-0
lines changed0 file changed
+0
-0
lines changed
0 commit comments