Patch SGL Benchmark Test for Pytest Dashboard

app_tests/benchmark_tests/llm/conftest.py

@@ -21,7 +21,6 @@ def pre_process_model(request, tmp_path_factory):
     settings = request.param["settings"]
     batch_sizes = request.param["batch_sizes"]
 
-    tmp_dir = tmp_path_factory.mktemp("llm_benchmark_test")
     mlir_path = tmp_dir / "model.mlir"
     config_path = tmp_dir / "config.json"
     vmfb_path = tmp_dir / "model.vmfb"

app_tests/benchmark_tests/llm/sglang_benchmark_test.py

@@ -38,7 +38,19 @@
 TOKENIZER_DIR = Path("/data/llama3.1/8b/")
 
 
-@pytest.mark.parametrize("request_rate", [1, 2, 4, 8, 16, 32])
+def log_jsonl_result(file_path):
+    with open(file_path, "r") as file:
+        json_string = file.readline().strip()
+
+    json_data = json.loads(json_string)
+    for key, val in json_data.items():
+        logger.info(f"{key.upper()}: {val}")
+
+
+@pytest.mark.parametrize(
+    "request_rate",
+    [1, 2, 4, 8, 16, 32],
+)
 @pytest.mark.parametrize(
     "pre_process_model",
     [
@@ -101,6 +113,8 @@ def test_sglang_benchmark_server(request_rate, pre_process_model):
             benchmark_process.join()
 
         logger.info(f"Benchmark run completed in {str(time.time() - start)} seconds")
+        logger.info("======== RESULTS ========")
+        log_jsonl_result(benchmark_args.output_file)
     except Exception as e:
         logger.info(e)
 

app_tests/benchmark_tests/llm/utils.py

@@ -37,6 +37,7 @@ def as_namespace(self) -> Namespace:
             dataset_name="sharegpt",
             random_input_len=None,
             random_output_len=None,
+            random_range_ratio=0.0,
             dataset_path="",
             sharegpt_output_len=None,
             multi=False,