[Benchmark] Do not save detailed info to json by default (#14879)

Signed-off-by: simon-mo <simon.mo@hey.com>

benchmarks/backend_request_func.py

@@ -14,7 +14,8 @@ from tqdm.asyncio import tqdm
 from transformers import (AutoTokenizer, PreTrainedTokenizer,
                           PreTrainedTokenizerFast)
 
-from vllm.model_executor.model_loader.weight_utils import get_lock
+# NOTE(simon): do not import vLLM here so the benchmark script
+# can run without vLLM installed.
 
 AIOHTTP_TIMEOUT = aiohttp.ClientTimeout(total=6 * 60 * 60)
 
@@ -427,6 +428,8 @@ def get_model(pretrained_model_name_or_path: str) -> str:
     if os.getenv('VLLM_USE_MODELSCOPE', 'False').lower() == 'true':
         from modelscope import snapshot_download
 
+        from vllm.model_executor.model_loader.weight_utils import get_lock
+
         # Use file lock to prevent multiple processes from
         # downloading the same model weights at the same time.
         with get_lock(pretrained_model_name_or_path):