[Executorch][llm] Add support for ring kv cache and ring attention (#10832)
Pull Request resolved: #10608 Introduced CachePositionManager to keep track of what is the position for each slot in ring kv cache. This is used to generate mask. ghstack-source-id: 283404678 @exported-using-ghexport Differential Revision: [D73891427](https://our.internmc.facebook.com/intern/diff/D73891427/)
P
pytorchbot committed
d7201abe5f7e9ad1f1758ca4f7460d8516840a85
Parent: 756f86a
Committed by GitHub <noreply@github.com>
on 5/13/2025, 12:21:26 AM