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
@@ -253,7 +253,7 @@ llama_model_wavtokenizer_dec::graph::graph(const llama_model & model, const llm_
LLM_NORM, -1);
// lm_head
cur = build_lora_mm(model.output, cur);
cur = build_lora_mm(model.output, cur, model.output_s);
cur = ggml_add(ctx0, cur, model.output_b);