talk-llama : sync llama.cpp

This commit is contained in:
Georgi Gerganov
2026-05-25 12:26:07 +03:00
parent 0a62a579cc
commit 865ec171aa
129 changed files with 1593 additions and 395 deletions
+1 -1
View File
@@ -186,7 +186,7 @@ llama_model_plamo3::graph<iswa>::graph(const llama_model & model, const llm_grap
cur = build_norm(cur, model.output_norm, NULL, LLM_NORM_RMS, -1);
res->t_embd = cur;
cur = build_lora_mm(model.output, cur);
cur = build_lora_mm(model.output, cur, model.output_s);
res->t_logits = cur;
ggml_build_forward_expand(gf, cur);