diff options
| author | fairydreaming <166155368+fairydreaming@users.noreply.github.com> | 2024-05-17 13:24:38 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-05-17 14:24:38 +0300 |
| commit | 27b040691cbe45314147c2745e891a38e9c048d4 (patch) | |
| tree | 85f2ade442a6e316a6700a89bb121924e051c593 /docs/BLIS.md | |
| parent | 29c60d8cddcfd14fa8a6bf023a6c4eb8692c76ba (diff) | |
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>
Diffstat (limited to 'docs/BLIS.md')
0 files changed, 0 insertions, 0 deletions