talk-llama : sync llama.cpp

This commit is contained in:
Georgi Gerganov
2026-05-02 15:02:42 +03:00
parent 18162bcf61
commit 4bf733672b
144 changed files with 3675 additions and 5535 deletions
+1 -1
View File
@@ -89,7 +89,7 @@ llm_build_olmo2<iswa>::llm_build_olmo2(const llama_model & model, const llm_grap
cb(Vcur, "Vcur", il);
cur = build_attn(inp_attn,
model.layers[il].wo, NULL,
model.layers[il].wo, NULL, model.layers[il].wo_s,
Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, 1.0f/sqrtf(float(n_embd_head)), il);
}
if (il == n_layer - 1 && inp_out_ids) {