diff --git a/vllm_ascend/worker/model_runner_v1.py b/vllm_ascend/worker/model_runner_v1.py
index d6389402..4d97c1a1 100644
--- a/vllm_ascend/worker/model_runner_v1.py
+++ b/vllm_ascend/worker/model_runner_v1.py
@@ -567,7 +567,8 @@ class NPUModelRunner(GPUModelRunner):
         """
         # TODO: need refactor later, related to vllm PR #34043 this pr delete func
         # relax_for_mixed_batch_cudagraphs, num_reqs no longer equals the actual number of requests.
-        if cudagraph_runtime_mode == CUDAGraphMode.FULL:
+        if cudagraph_runtime_mode == CUDAGraphMode.FULL and \
+            self.compilation_config.cudagraph_mode == CUDAGraphMode.FULL:
             num_reqs_padded = num_reqs
         else:
             num_reqs_padded = batch_desc_num_reqs if batch_desc_num_reqs is not None else num_reqs