A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 03:30 UTC
[Frontend] fix duplicate output for bench subcmd (#20446)
Signed-off-by: reidliu41 <reid201711@gmail.com>
Reid committed
Jul 3, 2025 at 23:02 UTC
619b9f5c7e51fed230a0c9d2a1a5cca85d1651b9
1 file changed
+1
vllm/entrypoints/cli/benchmark/main.py
+1
@@ -44,6 +44,7 @@ class BenchmarkSubcommand(CLISubcommand):
44
cmd_cls.name,
45
help=cmd_cls.help,
46
description=cmd_cls.help,
47
+ usage=f"vllm bench {cmd_cls.name} [options]",
48
)
49
cmd_subparser.set_defaults(dispatch_function=cmd_cls.cmd)
50
cmd_cls.add_cli_args(cmd_subparser)