From 71aea45c41bc32e0329152975b656465a273ee6d Mon Sep 17 00:00:00 2001 From: elvischenv <219235043+elvischenv@users.noreply.github.com> Date: Tue, 11 Nov 2025 17:32:24 +0800 Subject: [PATCH] [Fix] Add TPOT back to bench_serving (#12976) --- python/sglang/bench_serving.py | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/python/sglang/bench_serving.py b/python/sglang/bench_serving.py index 44bcadf7c..574b81f47 100644 --- a/python/sglang/bench_serving.py +++ b/python/sglang/bench_serving.py @@ -2052,6 +2052,12 @@ async def benchmark( print("{:<40} {:<10.2f}".format("Mean TTFT (ms):", metrics.mean_ttft_ms)) print("{:<40} {:<10.2f}".format("Median TTFT (ms):", metrics.median_ttft_ms)) print("{:<40} {:<10.2f}".format("P99 TTFT (ms):", metrics.p99_ttft_ms)) + print( + "{s:{c}^{n}}".format(s="Time per Output Token (excl. 1st token)", n=50, c="-") + ) + print("{:<40} {:<10.2f}".format("Mean TPOT (ms):", metrics.mean_tpot_ms)) + print("{:<40} {:<10.2f}".format("Median TPOT (ms):", metrics.median_tpot_ms)) + print("{:<40} {:<10.2f}".format("P99 TPOT (ms):", metrics.p99_tpot_ms)) print("{s:{c}^{n}}".format(s="Inter-Token Latency", n=50, c="-")) print("{:<40} {:<10.2f}".format("Mean ITL (ms):", metrics.mean_itl_ms)) print("{:<40} {:<10.2f}".format("Median ITL (ms):", metrics.median_itl_ms))