Check A100 inference time (reviewers ignore this commit)

triton-inference-server · Aug 14, 2024 · b24fef2 · b24fef2
1 parent c476337
commit b24fef2
Showing 1 changed file with 2 additions and 0 deletions.
diff --git a/ci/L0_backend_vllm/metrics_test/vllm_metrics_test.py b/ci/L0_backend_vllm/metrics_test/vllm_metrics_test.py
@@ -119,6 +119,8 @@ def test_vllm_metrics(self):
             model_name=self.vllm_model_name,
         )
         metrics_dict = self.get_vllm_metrics()
+        # Test CI job L0_backend_vllm--A100-base A100 inference time. Reviewers disregard print statement.
+        print(metrics_dict)
 
         # vllm:prompt_tokens_total
         self.assertEqual(metrics_dict["vllm:prompt_tokens_total"], 18)