cuda : fix compile warnings (whisper/0)

diff --git a/ggml/src/ggml-cuda/ggml-cuda.cu b/ggml/src/ggml-cuda/ggml-cuda.cu
index e9e9592ebad1eb4450b80ebf5d13f52ceb280a23..08383edb40290c5bb3f6d4c35b8c60a15a770f54 100644 (file)
--- a/ggml/src/ggml-cuda/ggml-cuda.cu
+++ b/ggml/src/ggml-cuda/ggml-cuda.cu
@@ -3910,14 +3910,14 @@ static void ggml_cuda_graph_evaluate_and_capture(ggml_backend_cuda_context * cud
         // Launch graph
         CUDA_CHECK(cudaGraphLaunch(graph->instance, cuda_ctx->stream()));
 #else
+        GGML_UNUSED(graph_key);
         graph_evaluated_or_captured = true;
 #endif  // USE_CUDA_GRAPH
     }
 }
 
-static bool ggml_cuda_graph_set_enabled(ggml_backend_cuda_context * cuda_ctx, const void * graph_key) {
-
 #ifdef USE_CUDA_GRAPH
+static bool ggml_cuda_graph_set_enabled(ggml_backend_cuda_context * cuda_ctx, const void * graph_key) {
     ggml_cuda_graph * graph = cuda_ctx->cuda_graph(graph_key);
 
     if (graph->graph == nullptr) {
@@ -3930,12 +3930,8 @@ static bool ggml_cuda_graph_set_enabled(ggml_backend_cuda_context * cuda_ctx, co
     }
 
     return graph->is_enabled();
-#else
-    GGML_UNUSED(cuda_ctx);
-    GGML_UNUSED(graph_key);
-    return false;
-#endif // USE_CUDA_GRAPH
 }
+#endif // USE_CUDA_GRAPH
 
 static enum ggml_status ggml_backend_cuda_graph_compute(ggml_backend_t backend, ggml_cgraph * cgraph) {
     ggml_backend_cuda_context * cuda_ctx = (ggml_backend_cuda_context *) backend->context;