root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-26 03:14:35 +00:00
Code Issues Actions 7 Packages Projects Releases Wiki Activity

fix: divide 0 exception in mamba (#7932)

Browse Source 
Signed-off-by: thxCode <thxcode0824@gmail.com>
This commit is contained in:
Frank Mai 2024-06-17 22:11:08 +08:00 committed by GitHub
parent 6a2f0b3474
commit c637fcd34d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
llama.cpp
View File

@ -5383,7 +5383,7 @@ static bool llm_load_tensors(
// create tensors for the weights // create tensors for the weights
{ {
const int64_t n_embd = hparams.n_embd; const int64_t n_embd = hparams.n_embd;
const int64_t n_embd_head = n_embd / hparams.n_head; const int64_t n_embd_head = (hparams.n_head == 0) ? 0 : n_embd / hparams.n_head;
const int64_t n_embd_k_gqa = hparams.n_embd_k_gqa(); const int64_t n_embd_k_gqa = hparams.n_embd_k_gqa();
const int64_t n_embd_v_gqa = hparams.n_embd_v_gqa(); const int64_t n_embd_v_gqa = hparams.n_embd_v_gqa();
const int64_t n_embd_gqa = n_embd_v_gqa; const int64_t n_embd_gqa = n_embd_v_gqa;