Check A100 inference time (reviewers ignore this commit)

yinggeh · yinggeh · commit b24fef2cacab · 2024-08-13T20:20:16.000-07:00
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)

Original file line number	Diff line number	Diff line change
`@@ -119,6 +119,8 @@ def test_vllm_metrics(self):`
`119`	`119`	`model_name=self.vllm_model_name,`
`120`	`120`	`)`
`121`	`121`	`metrics_dict = self.get_vllm_metrics()`
	`122`	`+ # Test CI job L0_backend_vllm--A100-base A100 inference time. Reviewers disregard print statement.`
	`123`	`+ print(metrics_dict)`
`122`	`124`
`123`	`125`	`# vllm:prompt_tokens_total`
`124`	`126`	`self.assertEqual(metrics_dict["vllm:prompt_tokens_total"], 18)`