model : fix llama_model::n_gpu_layers() (#24188)

diff --git a/src/llama-model.cpp b/src/llama-model.cpp
index c98cb27e4d4620c90959c4a2c2ca29775c6728c0..1f442d8a322f9818ca1269daa7ea405e13cf3bc4 100644 (file)
--- a/src/llama-model.cpp
+++ b/src/llama-model.cpp
@@ -1636,7 +1636,8 @@ const float * llama_model::tensor_split() const {
 }
 
 uint32_t llama_model::n_gpu_layers() const {
-    return params.n_gpu_layers >= 0 ? params.n_gpu_layers : hparams.n_layer() + 1;
+    // note: plus 1 for the "output" layer
+    return params.n_gpu_layers >= 0 ? params.n_gpu_layers : hparams.n_layer_all + 1;
 }
 
 llama_split_mode llama_model::split_mode() const {