public_git/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-10-17 11:45:38 +02:00
Code Issues Packages Projects Releases Wiki Activity

talk-llama : sync llama.cpp

Browse Source
This commit is contained in:
Georgi Gerganov
2026-02-08 09:29:10 +02:00
parent b0e81c1a2e
commit 4b23ff249e
26 changed files with 1661 additions and 179 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/talk-llama/models/openelm.cpp
+1 -1
View File
@@ -43,7 +43,7 @@ llm_build_openelm::llm_build_openelm(const llama_model & model, const llm_graph_
ggml_tensor * Kcur = ggml_view_3d(ctx0, cur, n_embd_head, n_head_kv, n_tokens, cur->nb[1], cur->nb[2], cur->nb[1]*n_head);
cb(Kcur, "Kcur", il);
ggml_tensor * Vcur = ggml_cont(ctx0, ggml_view_3d(ctx0, cur, n_embd_head, n_head_kv, n_tokens, cur->nb[1], cur->nb[2], cur->nb[1]*(n_head+n_head_kv)));
ggml_tensor * Vcur = ggml_view_3d(ctx0, cur, n_embd_head, n_head_kv, n_tokens, cur->nb[1], cur->nb[2], cur->nb[1]*(n_head+n_head_kv));
cb(Vcur, "Vcur", il);
Qcur = build_norm(Qcur,