You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
// TODO: Extend the solution to make it work for batch size > 1 and num beams > 1
357
357
// Phi3 model switches from short factor to long factor at 4097 (original_max_position_embeddings+1) token, needs Recomputation of Position IDs and KV Cache
358
358
// at this stage which is achieved by rewinding to zero and appending the current sequence
0 commit comments