vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-12 01:54:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

not working merge

Browse source
This commit is contained in:
Concedo 2023-11-02 17:52:40 +08:00
commit bc4ff72317
38 changed files with 886 additions and 360 deletions
Download patch file Download diff file Expand all files Collapse all files

4
otherarch/llama_v3.cpp
View file

@ -1614,11 +1614,11 @@ static struct ggml_cgraph * llama_v3_build_graph(
}
#endif
struct ggml_tensor * Kcur = ggml_rope_custom_inplace(ctx0, ggml_reshape_3d(ctx0, tmpk, n_embd_head, n_head_kv, N), KQ_pos, n_embd_head, 0, 0, freq_base, freq_scale);
struct ggml_tensor *Kcur = ggml_rope_custom_inplace(ctx0, ggml_reshape_3d(ctx0, tmpk, n_embd_head, n_head_kv, N), KQ_pos, n_embd_head, 0, 0, 0, freq_base, freq_scale, 0, 0, 0, 0);
offload_func_kq(Kcur);
ggml_set_name(Kcur, "Kcur");
struct ggml_tensor * Qcur = ggml_rope_custom_inplace(ctx0, ggml_reshape_3d(ctx0, tmpq, n_embd_head, n_head, N), KQ_pos, n_embd_head, 0, 0, freq_base, freq_scale);
struct ggml_tensor *Qcur = ggml_rope_custom_inplace(ctx0, ggml_reshape_3d(ctx0, tmpq, n_embd_head, n_head, N), KQ_pos, n_embd_head, 0, 0, 0, freq_base, freq_scale, 0, 0, 0, 0);
offload_func_kq(Qcur);
ggml_set_name(Qcur, "Qcur");