[Frontend] run-batch supports V1 (vllm-project#21541)

Signed-off-by: DarkLight1337 <[email protected]>

Author: DarkLight1337

throughput.py

@@ -148,7 +148,9 @@ async def run_vllm_async(
     from vllm import SamplingParams
 
     async with build_async_engine_client_from_engine_args(
-            engine_args, disable_frontend_multiprocessing) as llm:
+        engine_args,
+        disable_frontend_multiprocessing=disable_frontend_multiprocessing,
+    ) as llm:
         model_config = await llm.get_model_config()
         assert all(
             model_config.max_model_len >= (request.prompt_len +