diff --git a/src/nemo_run/core/execution/base.py b/src/nemo_run/core/execution/base.py
index 2504fd6..cd86498 100644
--- a/src/nemo_run/core/execution/base.py
+++ b/src/nemo_run/core/execution/base.py
@@ -50,6 +50,7 @@ def get_nsys_prefix(self, profile_dir: str) -> Optional[list[str]]:
                 "true",
                 "--capture-range=cudaProfilerApi",
                 "--capture-range-end=stop",
+                "--cuda-graph-trace=node",
             ]
             return args
 
diff --git a/test/core/execution/test_slurm.py b/test/core/execution/test_slurm.py
index c280dbe..8ab4cad 100644
--- a/test/core/execution/test_slurm.py
+++ b/test/core/execution/test_slurm.py
@@ -508,6 +508,7 @@ def test_dummy_batch_request_nsys(
             "true",
             "--capture-range=cudaProfilerApi",
             "--capture-range-end=stop",
+            "--cuda-graph-trace=node",
         ]
 
     def test_dummy_batch_request_warn(