add latency

benchmarks/benchmark_throughput.py

@@ -458,6 +458,7 @@ def main(args: argparse.Namespace):
         # TODO(vllm-project/vllm/issues/9778): Count multi-modal token length.
         # vllm-chat backend counts the image tokens now
 
+    print(f"Latency: {elapsed_time:.2f} s")
     print(f"Throughput: {len(requests) / elapsed_time:.2f} requests/s, "
           f"{total_num_tokens / elapsed_time:.2f} total tokens/s, "
           f"{total_output_tokens / elapsed_time:.2f} output tokens/s")

vllm/benchmarks/benchmark_throughput.py

@@ -458,6 +458,7 @@ def main(args: argparse.Namespace):
         # TODO(vllm-project/vllm/issues/9778): Count multi-modal token length.
         # vllm-chat backend counts the image tokens now
 
+    print(f"Latency: {elapsed_time:.2f} s")
     print(f"Throughput: {len(requests) / elapsed_time:.2f} requests/s, "
           f"{total_num_tokens / elapsed_time:.2f} total tokens/s, "
           f"{total_output_tokens / elapsed_time:.2f} output tokens/s")