add latency

benchmarks/benchmark_throughput.py

@@ -443,6 +443,7 @@ def main(args: argparse.Namespace):
               "following metrics are not accurate because image tokens are not"
               " counted. See vllm-project/vllm/issues/9778 for details.")
         # TODO(vllm-project/vllm/issues/9778): Count molti-modal token length.
+    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

+# SPDX-License-Identifier: Apache-2.0
 """Benchmark offline inference throughput."""
 import argparse
 import dataclasses
@@ -442,6 +443,7 @@ def main(args: argparse.Namespace):
               "following metrics are not accurate because image tokens are not"
               " counted. See vllm-project/vllm/issues/9778 for details.")
         # TODO(vllm-project/vllm/issues/9778): Count molti-modal token length.
+    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")