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)

help class-attribute instance-attribute 

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

name class-attribute instance-attribute 

name = 'latency'

add_cli_args classmethod 

add_cli_args(parser: ArgumentParser) -> None
Source code in vllm/entrypoints/cli/benchmark/latency.py 
15
16
17
@classmethod
def add_cli_args(cls, parser: argparse.ArgumentParser) -> None:
    add_cli_args(parser)

cmd staticmethod 

cmd(args: Namespace) -> None
Source code in vllm/entrypoints/cli/benchmark/latency.py 
19
20
21
@staticmethod
def cmd(args: argparse.Namespace) -> None:
    main(args)