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

fix merge

Browse source
This commit is contained in:
slaren 2024-03-13 18:22:22 +01:00
parent 9092883d58
commit cb580a6493
1 changed files with 1 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama.cpp
View file

@ -6550,10 +6550,6 @@ struct llm_build_context {
ext_factor, attn_factor, beta_fast, beta_slow ext_factor, attn_factor, beta_fast, beta_slow
); );
cb(Kcur, "Kcur", il); cb(Kcur, "Kcur", il);
cur = llm_build_kv(ctx0, model, hparams, kv_self, gf,
model.layers[il].wo, model.layers[il].bo,
Kcur, Vcur, Qcur, KQ_mask, nullptr, n_ctx, n_tokens, kv_head, n_kv, 1.0f/sqrtf(float(n_embd_head)), cb, il);
} }
struct ggml_tensor * q = ggml_permute(ctx0, Qcur, 0, 2, 1, 3); struct ggml_tensor * q = ggml_permute(ctx0, Qcur, 0, 2, 1, 3);