vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

cleanup

Browse source
This commit is contained in:
Andrei Betlen 2024-06-27 13:43:45 -04:00
parent 6913a17bf5
commit 06f1ba410e
1 changed files with 2 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

5
src/llama.cpp
View file

@ -10992,7 +10992,7 @@ struct llm_build_context {
return gf;
}
struct ggml_cgraph * build_gemma2() {
struct ggml_cgraph * gf = ggml_new_graph_custom(ctx0, LLAMA_MAX_NODES, false);
@ -11050,8 +11050,7 @@ struct llm_build_context {
model.layers[il].wo, NULL,
Kcur, Vcur, Qcur, KQ_mask, n_tokens, kv_head, n_kv, 1.0f, cb, il);
}
// is this the right place for it?
cur = llm_build_norm(ctx0, cur, hparams,
model.layers[il].attn_post_norm, NULL,
LLM_NORM_RMS, cb, il);