diff --git a/ggml/src/ggml-cuda/ggml-cuda.cu b/ggml/src/ggml-cuda/ggml-cuda.cu
index 0b06be729..715606f32 100644
--- a/ggml/src/ggml-cuda/ggml-cuda.cu
+++ b/ggml/src/ggml-cuda/ggml-cuda.cu
@@ -2337,6 +2337,28 @@ static bool ggml_graph_node_has_matching_properties(ggml_tensor * node, ggml_gra
 }
 #endif
 
+
+#ifdef USE_CUDA_GRAPH
+static void update_cuda_graph_executable(ggml_backend_cuda_context * cuda_ctx) {
+
+    cudaGraphExecUpdateResultInfo result_info;
+    cudaError_t stat = cudaGraphExecUpdate(cuda_ctx->cuda_graph->instance, cuda_ctx->cuda_graph->graph, &result_info);
+    if (stat == cudaErrorGraphExecUpdateFailure) {
+#ifndef NDEBUG
+        GGML_LOG_DEBUG("%s: CUDA graph update failed\n", __func__);
+#endif
+        // The pre-existing graph exec cannot be updated due to violated constraints
+        // so instead clear error and re-instantiate
+        cudaGetLastError();
+        CUDA_CHECK(cudaGraphExecDestroy(cuda_ctx->cuda_graph->instance));
+        cuda_ctx->cuda_graph->instance = nullptr;
+        CUDA_CHECK(cudaGraphInstantiate(&cuda_ctx->cuda_graph->instance, cuda_ctx->cuda_graph->graph, NULL, NULL, 0));
+    } else {
+        GGML_ASSERT(stat == cudaSuccess);
+    }
+}
+#endif
+
 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;
 
@@ -2585,21 +2607,8 @@ static enum ggml_status ggml_backend_cuda_graph_compute(ggml_backend_t backend,
         }
 
         // Update graph executable
-        cudaGraphExecUpdateResultInfo result_info;
-        cudaError_t stat = cudaGraphExecUpdate(cuda_ctx->cuda_graph->instance, cuda_ctx->cuda_graph->graph, &result_info);
-        if (stat == cudaErrorGraphExecUpdateFailure) {
-#ifndef NDEBUG
-            GGML_LOG_DEBUG("%s: CUDA graph update failed\n", __func__);
-#endif
-            // The pre-existing graph exec cannot be updated due to violated constraints
-            // so instead clear error and re-instantiate
-            cudaGetLastError();
-            CUDA_CHECK(cudaGraphExecDestroy(cuda_ctx->cuda_graph->instance));
-            cuda_ctx->cuda_graph->instance = nullptr;
-            CUDA_CHECK(cudaGraphInstantiate(&cuda_ctx->cuda_graph->instance, cuda_ctx->cuda_graph->graph, NULL, NULL, 0));
-        } else {
-            GGML_ASSERT(stat == cudaSuccess);
-        }
+        update_cuda_graph_executable(cuda_ctx);
+
         // Launch graph
         CUDA_CHECK(cudaGraphLaunch(cuda_ctx->cuda_graph->instance, cuda_ctx->stream()));
 #else