mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-12-24 13:28:13 +08:00
6fd3e72da1
* bench command * bench command * bench command * bench command * bench command --------- Co-authored-by: K11OntheBoat <your_email@example.com>
38 lines
1.3 KiB
Python
38 lines
1.3 KiB
Python
"""
|
|
# Copyright (c) 2025 PaddlePaddle Authors. All Rights Reserved.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License"
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
"""
|
|
|
|
# This file is modified from https://github.com/vllm-project/vllm/blob/main/vllm/benchmarks/latency.py
|
|
|
|
import argparse
|
|
|
|
from fastdeploy.benchmarks.latency import add_cli_args, main
|
|
from fastdeploy.entrypoints.cli.benchmark.base import BenchmarkSubcommandBase
|
|
|
|
|
|
class BenchmarkLatencySubcommand(BenchmarkSubcommandBase):
|
|
"""The `latency` subcommand for fastdeploy 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)
|