Skip to content

vllm.entrypoints.cli.benchmark.latency

BenchmarkLatencySubcommand

Bases: BenchmarkSubcommandBase

The latency subcommand for vllm bench.

Source code in vllm/entrypoints/cli/benchmark/latency.py 
 9
10
11
12
13
14
15
16
17
18
19
20
21
class BenchmarkLatencySubcommand(BenchmarkSubcommandBase):
    """The `latency` subcommand for `vllm bench`."""

    name = "latency"
    help = "Benchmark the latency of a single batch of requests."

    @classmethod
    def add_cli_args(cls, parser: argparse.ArgumentParser) -> None:
        add_cli_args(parser)

    @staticmethod
    def cmd(args: argparse.Namespace) -> None:
        main(args)