talk-llama : fix build after ggml sync (#1049)

sed -i 's,GGML_BACKEND_CUDA,GGML_BACKEND_GPU,g' examples/talk-llama/llama.cpp

diff --git a/examples/talk-llama/llama.cpp b/examples/talk-llama/llama.cpp
index 4cbc8d6b63752359f7de4b2c20600bfe9f4c703f..942407b84a3f3234c1f6f175c2c2758fe5a118f6 100644 (file)
--- a/examples/talk-llama/llama.cpp
+++ b/examples/talk-llama/llama.cpp
@@ -1002,7 +1002,7 @@ static void llama_model_load_internal(
     }
 
 #ifdef GGML_USE_CUBLAS
-#define LLAMA_BACKEND_OFFLOAD GGML_BACKEND_CUDA
+#define LLAMA_BACKEND_OFFLOAD GGML_BACKEND_GPU
 #else
 #define LLAMA_BACKEND_OFFLOAD GGML_BACKEND_CPU
 #endif
@@ -1054,7 +1054,7 @@ static void llama_model_load_internal(
             layer.w2 = ml->get_tensor(layers_i + ".feed_forward.w2.weight", {  n_ff,   n_embd}, backend);
             layer.w3 = ml->get_tensor(layers_i + ".feed_forward.w3.weight", {n_embd,   n_ff},   backend);
 
-            if (backend == GGML_BACKEND_CUDA) {
+            if (backend == GGML_BACKEND_GPU) {
                 vram_total +=
                     ggml_nbytes(layer.attention_norm) + ggml_nbytes(layer.wq) + ggml_nbytes(layer.wk)             +
                     ggml_nbytes(layer.wv)             + ggml_nbytes(layer.wo) + ggml_nbytes(layer.attention_norm) +
@@ -1115,7 +1115,7 @@ static void llama_model_load_internal(
             }
         }
         for (llama_load_tensor & lt : ml->tensors_map.tensors) {
-            if (lt.ggml_tensor->backend != GGML_BACKEND_CUDA) {
+            if (lt.ggml_tensor->backend != GGML_BACKEND_GPU) {
                 continue;
             }
             if (progress_callback) {