File tree 1 file changed +4
-4
lines changed
1 file changed +4
-4
lines changed Original file line number Diff line number Diff line change @@ -2683,8 +2683,8 @@ static void llm_load_tensors(
2683
2683
2684
2684
// output
2685
2685
{
2686
- ggml_backend backend_norm;
2687
- ggml_backend backend_output;
2686
+ ggml_backend_type backend_norm;
2687
+ ggml_backend_type backend_output;
2688
2688
2689
2689
if (n_gpu_layers > int(n_layer)) {
2690
2690
// 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(
2719
2719
model.layers.resize(n_layer);
2720
2720
2721
2721
for (uint32_t i = 0; i < n_layer; ++i) {
2722
- const ggml_backend backend = int(i) < i_gpu_start ? GGML_BACKEND_CPU : LLAMA_BACKEND_OFFLOAD; // NOLINT
2723
- const ggml_backend backend_split = int(i) < i_gpu_start ? GGML_BACKEND_CPU : LLAMA_BACKEND_OFFLOAD_SPLIT; // NOLINT
2722
+ const ggml_backend_type backend = int(i) < i_gpu_start ? GGML_BACKEND_CPU : LLAMA_BACKEND_OFFLOAD; // NOLINT
2723
+ const ggml_backend_type backend_split = int(i) < i_gpu_start ? GGML_BACKEND_CPU : LLAMA_BACKEND_OFFLOAD_SPLIT; // NOLINT
2724
2724
2725
2725
auto & layer = model.layers[i];
2726
2726
You can’t perform that action at this time.
0 commit comments