From f2a90094c93a9ebd3cd9a6f8b54ed667e1d9bd96 Mon Sep 17 00:00:00 2001
From: Cheng Wan <54331508+ch-wan@users.noreply.github.com>
Date: Tue, 12 May 2026 23:46:47 -0700
Subject: [PATCH] bench: fix wrong flag names in bench_one_batch{,_server}
 docstrings (#25143)

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---
 python/sglang/bench_one_batch.py        | 8 ++++----
 python/sglang/bench_one_batch_server.py | 2 +-
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/python/sglang/bench_one_batch.py b/python/sglang/bench_one_batch.py
index dfc2846f4..6924b3036 100644
--- a/python/sglang/bench_one_batch.py
+++ b/python/sglang/bench_one_batch.py
@@ -8,14 +8,14 @@ It accepts server arguments (the same as launch_server.py) and benchmark argumen
 ## with dummy weights:
 python -m sglang.bench_one_batch --model-path meta-llama/Meta-Llama-3-8B-Instruct --load-format dummy
 ## sweep through multiple data points and store (append) the results in a jsonl file:
-python -m sglang.bench_one_batch --model-path meta-llama/Meta-Llama-3-8B-Instruct --batch 1 12 14 --input-len 256 512 --output-len 32 256 --run-name test_run
+python -m sglang.bench_one_batch --model-path meta-llama/Meta-Llama-3-8B-Instruct --batch-size 1 12 14 --input-len 256 512 --output-len 32 256 --run-name test_run
 ## run with profiling:
-python -m sglang.bench_one_batch --model-path meta-llama/Meta-Llama-3-8B-Instruct --batch 1 12 14 --input-len 256 512 --profile
+python -m sglang.bench_one_batch --model-path meta-llama/Meta-Llama-3-8B-Instruct --batch-size 1 12 14 --input-len 256 512 --profile
 ## run with profiling to custom directory:
 export SGLANG_TORCH_PROFILER_DIR=/root/sglang/profile_log
-python -m sglang.bench_one_batch --model-path meta-llama/Meta-Llama-3-8B-Instruct --batch 1 --input-len 256 --profile
+python -m sglang.bench_one_batch --model-path meta-llama/Meta-Llama-3-8B-Instruct --batch-size 1 --input-len 256 --profile
 ## run with CUDA profiler (nsys):
-nsys profile --force-overwrite=true -o bench_one_batch python -m sglang.bench_one_batch --model-path meta-llama/Meta-Llama-3-8B-Instruct --batch 1 --input-len 256 --profile --profile-activities CUDA_PROFILER
+nsys profile --force-overwrite=true -o bench_one_batch python -m sglang.bench_one_batch --model-path meta-llama/Meta-Llama-3-8B-Instruct --batch-size 1 --input-len 256 --profile --profile-activities CUDA_PROFILER
 # Usage (correctness test):
 python -m sglang.bench_one_batch --model-path TinyLlama/TinyLlama-1.1B-Chat-v0.4 --correct
 
diff --git a/python/sglang/bench_one_batch_server.py b/python/sglang/bench_one_batch_server.py
index a2d8325f8..c6e6cf1c1 100644
--- a/python/sglang/bench_one_batch_server.py
+++ b/python/sglang/bench_one_batch_server.py
@@ -9,7 +9,7 @@ python3 -m sglang.bench_one_batch_server --model meta-llama/Meta-Llama-3.1-8B --
 
 python3 -m sglang.bench_one_batch_server --model None --base-url http://localhost:30000 --batch-size 16 --input-len 1024 --output-len 8
 python3 -m sglang.bench_one_batch_server --model None --base-url http://localhost:30000 --batch-size 16 --input-len 1024 --output-len 8 --show-report --profile --profile-by-stage
-python3 -m sglang.bench_one_batch_server --model None --base-url http://localhost:30000 --batch-size 16 --input-len 1024 --output-len 8 --output-path results.json --profile
+python3 -m sglang.bench_one_batch_server --model None --base-url http://localhost:30000 --batch-size 16 --input-len 1024 --output-len 8 --result-filename results.jsonl --profile
 """
 
 import argparse