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

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-07-25 11:05:55 +08:00
parent fe56180c7f
commit 34ddcf9ff4
5 changed files with 56 additions and 25 deletions
--- a/benchmarks/benchmark_throughput.py
+++ b/benchmarks/benchmark_throughput.py
@@ -167,7 +167,8 @@ async def run_vllm_async(
    from vllm import SamplingParams

    async with build_async_engine_client_from_engine_args(
-        engine_args, disable_frontend_multiprocessing
+        engine_args,
+        disable_frontend_multiprocessing=disable_frontend_multiprocessing,
    ) as llm:
        model_config = await llm.get_model_config()
        assert all(