quant : fix quantizing moe with mtp (#24986)

diff --git a/src/llama-quant.cpp b/src/llama-quant.cpp
index 89b7fe8d4301897b30c7e1d94711811ab18c3f6e..847e79f46552c7cbf882c16fae0cecc22550d523 100644 (file)
--- 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;
 }
 
 //