CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-08 10:07:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

minor fix

Browse Source
This commit is contained in:
younesbelkada
2025-07-03 17:12:05 +04:00
parent 0c93ef6a9c
commit fdd5cff4ba
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
src/llama-model.cpp
View File

@@ -10203,7 +10203,7 @@ struct llm_build_mamba : public llm_graph_context {
// {n_embd, n_seq_tokens, n_seqs} => {n_embd, n_tokens} // {n_embd, n_seq_tokens, n_seqs} => {n_embd, n_tokens}
cur = ggml_reshape_2d(ctx0, cur, cur->ne[0], n_seq_tokens * n_seqs); cur = ggml_reshape_2d(ctx0, cur, cur->ne[0], n_seq_tokens * n_seqs);
// cb(cur, "mamba_out", il); cb(cur, "mamba_out", il);
return cur; return cur;
} }
@@ -14697,6 +14697,7 @@ struct llm_build_falcon_h1 : public llm_graph_context {
Qcur = ggml_reshape_3d(ctx0, Qcur, n_embd_head, n_head, n_tokens); Qcur = ggml_reshape_3d(ctx0, Qcur, n_embd_head, n_head, n_tokens);
Kcur = ggml_reshape_3d(ctx0, Kcur, n_embd_head, n_head_kv, n_tokens); Kcur = ggml_reshape_3d(ctx0, Kcur, n_embd_head, n_head_kv, n_tokens);
Kcur = ggml_scale(ctx0, Kcur, hparams.key_multiplier); Kcur = ggml_scale(ctx0, Kcur, hparams.key_multiplier);
Vcur = ggml_reshape_3d(ctx0, Vcur, n_embd_head, n_head_kv, n_tokens); Vcur = ggml_reshape_3d(ctx0, Vcur, n_embd_head, n_head_kv, n_tokens);