From 794a7875ee0df7d2c12ff0ba83b76438ca68bf26 Mon Sep 17 00:00:00 2001 From: Matthew Bonanni Date: Wed, 10 Dec 2025 12:44:02 -0500 Subject: [PATCH] [Misc] Consistent case for `vllm bench serve` results (#30403) Signed-off-by: Matthew Bonanni --- benchmarks/benchmark_serving_structured_output.py | 2 +- docs/benchmarking/cli.md | 2 +- vllm/benchmarks/serve.py | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/benchmarks/benchmark_serving_structured_output.py b/benchmarks/benchmark_serving_structured_output.py index a4e1b163dcca9..33aca831883aa 100644 --- a/benchmarks/benchmark_serving_structured_output.py +++ b/benchmarks/benchmark_serving_structured_output.py @@ -574,7 +574,7 @@ async def benchmark( ) print( "{:<40} {:<10.2f}".format( - "Total Token throughput (tok/s):", metrics.total_token_throughput + "Total token throughput (tok/s):", metrics.total_token_throughput ) ) diff --git a/docs/benchmarking/cli.md b/docs/benchmarking/cli.md index 1ce6b611745b1..dd5a12e408b02 100644 --- a/docs/benchmarking/cli.md +++ b/docs/benchmarking/cli.md @@ -84,7 +84,7 @@ Total input tokens: 1369 Total generated tokens: 2212 Request throughput (req/s): 1.73 Output token throughput (tok/s): 382.89 -Total Token throughput (tok/s): 619.85 +Total token throughput (tok/s): 619.85 ---------------Time to First Token---------------- Mean TTFT (ms): 71.54 Median TTFT (ms): 73.88 diff --git a/vllm/benchmarks/serve.py b/vllm/benchmarks/serve.py index 2e2054a8a4b13..254e4d35e5350 100644 --- a/vllm/benchmarks/serve.py +++ b/vllm/benchmarks/serve.py @@ -788,7 +788,7 @@ async def benchmark( ) print( "{:<40} {:<10.2f}".format( - "Total Token throughput (tok/s):", metrics.total_token_throughput + "Total token throughput (tok/s):", metrics.total_token_throughput ) )