quant : fix quantizing moe with mtp (#24986)

2026-06-25 07:36:49 +02:00
parent e9fb3b3fc0
commit b3ce5cedf4
1 changed files with 1 additions and 1 deletions
--- a/src/llama-quant.cpp
+++ b/src/llama-quant.cpp
@@ -847,7 +847,7 @@ static void init_quantize_state_counters(quantize_state_impl & qs, std::vector<t
            qs.has_tied_embeddings = false;
        }
    }
-    qs.n_ffn_down = qs.n_ffn_gate = qs.n_ffn_up = (int)qs.model.hparams.n_layer();
+    qs.n_ffn_down = qs.n_ffn_gate = qs.n_ffn_up = (int)qs.model.hparams.n_layer_all;
 }

 //