Skip to main content

HS-QA

Project description

LLM 推理服务基准测试

本仓库包含了测试常见推理服务吞吐的代码以及相关的测试结果。

安装说明

基础环境

  • Python 3.9 或以上版本
  • Poetry (非必须)

请使用以下命令安装 Poetry:

pip install poetry

运行方式

[通过 pip 线上安装运行]

pip install ai_benchmarks
run-benchmark -h
run-app

[通过 pip手动构建安装运行]

  1. 构建包或以其他方式获取:

    cd ai-benchmarks && poetry build
    
  2. 安装包:

    pip install ai_benchmarks-x.x.x.tar.gz
    
  3. 接口运行方式:

    run-app
    
  4. 直接运行方式,-h查看帮助,默认执行配置文件默认测试端点:

    run-benchmark -h
    

[通过代码运行]

  1. 安装依赖:

    cd ai-benchmarks
    poetry安装
    poetry lock && poetry install
    requirements安装
    pip install -i https://mirrors.aliyun.com/pypi/simple/   -r .\requirements.txt
    
  2. benchmark.py 是主要的压测脚本,采用 asyncio、AsyncOpenAI 和 ProcessPoolExecutor等 实现多端压测框架。

  3. 直接运行压测:

    poetry run python -m inference.benchmark
    
  4. 启动接口压测:

    poetry run python -m inference.main
    
  5. 测试报告和结果:

    • 测试报告输出到 inference/report 文件夹。
    • 原始测试结果数据输出到 inference/results 文件夹,可使用 draw.ipynb 进行绘图。

配置文件说明

[section]                  # 支持多section
endpoint:                  # *必须提供一个有效的 endpoint
api_key:                   # 认证KEY
concurrent_requests:       # 同时并发的请求数
batch:                     # 执行批次
duration_enabled:          # 启用持续请求的时间限制(开启后不执行 concurrent_requests)[True/False]
duration_time:             # 请求持续时间,默认为 1 秒
duratio_interval:          # 持续/请求间隔,默认0.2秒
duration_batch:            # 请求持续时间内每次并发数量,默认为 10
ip:                        # 用户查询机器资源占用
username:                  # 用户名
password:                  # 密码
timeout:                   # 超时时间,默认 60 秒
max_retries:               # 最大重试次数,默认 1
max_connections:           # 最大连接数
max_keepalive_connections: # 最大保持活动连接数
model:                     # 自动获取,可手动添加
owned_by:                  # 自动获取,可手动添加
stream:                    # 流式回复默认关闭[True/False]
prompts:                   # 问题, 为空自动匹配默认问题, 格式 [{"id": 1, "prompt": "Output from 1 to 100"}, {"id": 2, "prompt": "List the top 10 most important people in history."},]

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

ai_benchmarks-0.1.6.tar.gz (4.2 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

ai_benchmarks-0.1.6-py3-none-any.whl (4.3 MB view details)

Uploaded Python 3

File details

Details for the file ai_benchmarks-0.1.6.tar.gz.

File metadata

  • Download URL: ai_benchmarks-0.1.6.tar.gz
  • Upload date:
  • Size: 4.2 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.4 CPython/3.12.1 Windows/11

File hashes

Hashes for ai_benchmarks-0.1.6.tar.gz
Algorithm Hash digest
SHA256 35f4208f5b654901ce027c04863e54d8c4d874a1170deecadb7e167ba0734b1f
MD5 c2e1cc2abac0960b36fe63d5d88c5ea2
BLAKE2b-256 e840c27e0270941d03f6b466ea7723978572c9f43f6cce97155352b7fed38623

See more details on using hashes here.

File details

Details for the file ai_benchmarks-0.1.6-py3-none-any.whl.

File metadata

  • Download URL: ai_benchmarks-0.1.6-py3-none-any.whl
  • Upload date:
  • Size: 4.3 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.4 CPython/3.12.1 Windows/11

File hashes

Hashes for ai_benchmarks-0.1.6-py3-none-any.whl
Algorithm Hash digest
SHA256 6b40f3729da47c2503d5ae6a3f7386fcd01e27c93d0f25ed9e825765f0826c1d
MD5 9a4b6d0ea7f6567af58a1a838edf63f1
BLAKE2b-256 ad7e91daf5dde4b51887cba1e562e4a3debd7b0df14abe0c755eb742dec494fb

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page