diff --git a/vllm_ascend/compilation/acl_graph.py b/vllm_ascend/compilation/acl_graph.py
index 060ecf98..579dfda3 100644
--- a/vllm_ascend/compilation/acl_graph.py
+++ b/vllm_ascend/compilation/acl_graph.py
@@ -202,10 +202,9 @@ class ACLGraphWrapper:
         # If we do not in main model and in full-graph mode when using merge-eagle-graph,
         # we do not need to synchronize.
         # When enable_enpu is on, model_runner orders update vs replay; skip here.
-        # When FULL + EAGLE draft (merge path), replay does not need this barrier.
+        # When EAGLE draft (merge path), replay does not need this barrier.
         is_draft_eagle = _EXTRA_CTX.is_draft_model and self.use_eagle
-        need_sync = self.runtime_mode == CUDAGraphMode.FULL and not is_draft_eagle
-        if not self.enable_enpu and need_sync:
+        if not self.enable_enpu and not is_draft_eagle:
             torch.npu.current_stream().synchronize()
         entry.aclgraph.replay()
         return entry.output