update

ggerganov · Oct 9, 2023 · 074bd14 · 074bd14
1 parent 3a54c1f
commit 074bd14
Showing 1 changed file with 4 additions and 4 deletions.
diff --git a/llama.cpp b/llama.cpp
@@ -2683,8 +2683,8 @@ static void llm_load_tensors(
 
                     // output
                     {
-                        ggml_backend backend_norm;
-                        ggml_backend backend_output;
+                        ggml_backend_type backend_norm;
+                        ggml_backend_type backend_output;
 
                         if (n_gpu_layers > int(n_layer)) {
                             // norm is not performance relevant on its own but keeping it in VRAM reduces data copying
@@ -2719,8 +2719,8 @@ static void llm_load_tensors(
                     model.layers.resize(n_layer);
 
                     for (uint32_t i = 0; i < n_layer; ++i) {
-                        const ggml_backend backend = int(i) < i_gpu_start ? GGML_BACKEND_CPU : LLAMA_BACKEND_OFFLOAD; // NOLINT
-                        const ggml_backend backend_split = int(i) < i_gpu_start ? GGML_BACKEND_CPU : LLAMA_BACKEND_OFFLOAD_SPLIT; // NOLINT
+                        const ggml_backend_type backend = int(i) < i_gpu_start ? GGML_BACKEND_CPU : LLAMA_BACKEND_OFFLOAD; // NOLINT
+                        const ggml_backend_type backend_split = int(i) < i_gpu_start ? GGML_BACKEND_CPU : LLAMA_BACKEND_OFFLOAD_SPLIT; // NOLINT
 
                         auto & layer = model.layers[i];