diff --git a/vllm/benchmarks/throughput.py b/vllm/benchmarks/throughput.py index 866365ac18eb9..78c0f8bbbda7a 100644 --- a/vllm/benchmarks/throughput.py +++ b/vllm/benchmarks/throughput.py @@ -221,6 +221,7 @@ async def run_vllm_async( detokenize=not disable_detokenize, ) ) + prompts.append(prompt) lora_requests.append(request.lora_request) generators = []