Print the number of tokens generated (#6773)
Pull Request resolved: https://github.com/pytorch/executorch/pull/6771 This is useful for verifying the correctness of AttentionSink. ghstack-source-id: 252993225 @exported-using-ghexport Differential Revision: [D65784095](https://our.internmc.facebook.com/intern/diff/D65784095/) Co-authored-by: Lunwen He <lwhecser@gmail.com>
P
pytorchbot committed
49756f669e9169d519d90706b0cf3fb9a2b90b17
Parent: 99ba779
Committed by GitHub <noreply@github.com>
on 11/12/2024, 4:47:01 PM