fairydreaming 16472b59b2 llama : use n_embd_head_v when reshaping kqv (#7327) ...

* llama : use n_embd_head_v instead of n_embd_head_k when reshaping kqv

* llama : use n_embd_v_gqa and n_embd_head_v instead of n_embd_k_gqa and n_embd_head_k when making a view of cached value vectors.

---------

Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>

2024-05-17 14:24:38 +03:00

728 KiB

Raw Blame History

View Raw