OpenModelZ ( mdz
) is tool to deploy your models to any cluster (GCP, AWS, Lambda labs, your home lab, or even a single machine).
Getting models into production is hard for data scientists and SREs. You need to configure the monitoring, logging, and scaling infrastructure, with the right security and permissions. And then setup the domain, SSL, and load balancer. This can take weeks or months of work even for a single model deployment.
You can now use mdz deploy to effortlessly deploy your models. OpenModelZ handles all the infrastructure setup for you. Each deployment gets a public subdomain, like http://jupyter-9pnxd.2.242.22.143.modelz.live
, making it easily accessible.
OpenModelZ provides the following features out-of-the-box:
mdz server start
.OpenModelZ is the foundational component of the ModelZ platform available at modelz.ai.
Get a server (could be a cloud VM, a home lab, or even a single machine) and run the mdz server start
command. OpenModelZ will bootstrap the server for you.
$ mdz server start 🚧 Creating the server... 🚧 Initializing the load balancer... 🚧 Initializing the GPU resource... 🚧 Initializing the server... 🚧 Waiting for the server to be ready... 🐋 Checking if the server is running... 🐳 The server is running at http://146.235.213.84.modelz.live 🎉 You could set the environment variable to get started! export MDZ_URL=http://146.235.213.84.modelz.live $ export MDZ_URL=http://146.235.213.84.modelz.live
Then you could deploy your model with a single command mdz deploy
and get the endpoint:
$ mdz deploy --image modelzai/gradio-stable-diffusion:23.03 --name sdw --port 7860 --gpu 1
Inference sd is created
$ mdz list
NAME ENDPOINT STATUS INVOCATIONS REPLICAS
sdw http://sdw-qh2n0y28ybqc36oc.146.235.213.84.modelz.live Ready 174 1/1
http://146.235.213.84.modelz.live/inference/sdw.default
mdz
You can install OpenModelZ using the following command:
pip install openmodelz
You could verify the installation by running the following command:
mdz
Once you've installed the mdz
you can start deploying models and experimenting with them.
mdz
It's super easy to bootstrap the mdz
server. You just need to find a server (could be a cloud VM, a home lab, or even a single machine) and run the mdz server start
command.
Notice: We may require the root permission to bootstrap the
mdz
server on port 80.
$ mdz server start
🚧 Creating the server...
🚧 Initializing the load balancer...
🚧 Initializing the GPU resource...
🚧 Initializing the server...
🚧 Waiting for the server to be ready...
🐋 Checking if the server is running...
Agent:
Version: v0.0.13
Build Date: 2023-07-19T09:12:55Z
Git Commit: 84d0171640453e9272f78a63e621392e93ef6bbb
Git State: clean
Go Version: go1.19.10
Compiler: gc
Platform: linux/amd64
🐳 The server is running at http://192.168.71.93.modelz.live
🎉 You could set the environment variable to get started!
export MDZ_URL=http://192.168.71.93.modelz.live
The internal IP address will be used as the default endpoint of your deployments. You could provide the public IP address of your server to the mdz server start
command to make it accessible from the outside world.
# Provide the public IP as an argument $ mdz server start 1.2.3.4
You could also specify the registry mirror to speed up the image pulling process. Here is an example:
$ mdz server start --mirror-endpoints https://docker.mirrors.sjtug.sjtu.edu.cn
Once you've bootstrapped the mdz
server, you can start deploying your first applications. We will use jupyter notebook as an example in this tutorial. You could use any docker image as your deployment.
$ mdz deploy --image jupyter/minimal-notebook:lab-4.0.3 --name jupyter --port 8888 --command "jupyter notebook --ip='*' --NotebookApp.token='' --NotebookApp.password=''" Inference jupyter is created $ mdz list NAME ENDPOINT STATUS INVOCATIONS REPLICAS jupyter http://jupyter-9pnxdkeb6jsfqkmq.192.168.71.93.modelz.live Ready 488 1/1 http://192.168.71.93/inference/jupyter.default
You could access the deployment by visiting the endpoint URL. The endpoint will be automatically generated for each deployment with the following format: <name>-<random-string>.<ip>.modelz.live
.
It is http://jupyter-9pnxdkeb6jsfqkmq.192.168.71.93.modelz.live
in this case. The endpoint could be accessed from the outside world as well if you've provided the public IP address of your server to the mdz server start
command.
You could also create API-based deployments. We will use OpenAI compatible API server with Bloomz 560M as an example in this tutorial.
$ mdz deploy --image modelzai/llm-bloomz-560m:23.07.4 --name simple-server Inference simple-server is created $ mdz list NAME ENDPOINT STATUS INVOCATIONS REPLICAS jupyter http://jupyter-9pnxdkeb6jsfqkmq.192.168.71.93.modelz.live Ready 488 1/1 http://192.168.71.93/inference/jupyter.default simple-server http://simple-server-lagn8m9m8648q6kx.192.168.71.93.modelz.live Ready 0 1/1 http://192.168.71.93/inference/simple-server.default
You could use OpenAI python package and the endpoint http://simple-server-lagn8m9m8648q6kx.192.168.71.93.modelz.live
in this case, to interact with the deployment.
import openai openai.api_base="http://simple-server-lagn8m9m8648q6kx.192.168.71.93.modelz.live" openai.api_key="any" # create a chat completion chat_completion = openai.ChatCompletion.create(model="bloomz", messages=[ {"role": "user", "content": "Who are you?"}, {"role": "assistant", "content": "I am a student"}, {"role": "user", "content": "What do you learn?"}, ], max_tokens=100)
You could scale your deployment by using the mdz scale
command.
$ mdz scale simple-server --replicas 3
The requests will be load balanced between the replicas of your deployment.
You could also tell the mdz
to autoscale your deployment based on the inflight requests. Please check out the Autoscaling documentation for more details.
Sometimes you may want to debug your deployment. You could use the mdz logs
command to get the logs of your deployment.
$ mdz logs simple-server simple-server-6756dd67ff-4bf4g: 10.42.0.1 - - [27/Jul/2023 02:32:16] "GET / HTTP/1.1" 200 - simple-server-6756dd67ff-4bf4g: 10.42.0.1 - - [27/Jul/2023 02:32:16] "GET / HTTP/1.1" 200 - simple-server-6756dd67ff-4bf4g: 10.42.0.1 - - [27/Jul/2023 02:32:17] "GET / HTTP/1.1" 200 -
You could also use the mdz exec
command to execute a command in the container of your deployment. You do not need to ssh into the server to do that.
$ mdz exec simple-server ps PID USER TIME COMMAND 1 root 0:00 /usr/bin/dumb-init /bin/sh -c python3 -m http.server 80 7 root 0:00 /bin/sh -c python3 -m http.server 80 8 root 0:00 python3 -m http.server 80 9 root 0:00 ps
$ mdz exec simple-server -ti bash bash-4.4#
Or you could port-forward the deployment to your local machine and debug it locally.
$ mdz port-forward simple-server 7860 Forwarding inference simple-server to local port 7860
You could add more servers to your cluster by using the mdz server join
command. The mdz
server will be bootstrapped on the server and join the cluster automatically.
$ mdz server join <internal ip address of the previous server> $ mdz server list NAME PHASE ALLOCATABLE CAPACITY node1 Ready cpu: 16 cpu: 16 mem: 32784748Ki mem: 32784748Ki gpu: 1 gpu: 1 node2 Ready cpu: 16 cpu: 16 mem: 32784748Ki mem: 32784748Ki gpu: 1 gpu: 1
You could label your servers to deploy your models to specific servers. For example, you could label your servers with gpu=true
and deploy your models to servers with GPUs.
$ mdz server label node3 gpu=true type=nvidia-a100 $ mdz deploy ... --node-labels gpu=true,type=nvidia-a100
OpenModelZ is inspired by the k3s and OpenFaaS, but designed specifically for machine learning deployment. We keep the core of the system simple, and easy to extend.
You do not need to read this section if you just want to deploy your models. But if you want to understand how OpenModelZ works, this section is for you.
<p align=center> <img src="https://user-images.githubusercontent.com/5100735/260627792-2e89f6b8-006c-4807-84a3-29b6785af812.png" alt="OpenModelZ" width="500"/> </p>OpenModelZ is composed of two components:
mdz server
to manage the servers. The data plane is designed to be stateless and scalable. You could easily scale the data plane by adding more servers to the cluster. It uses k3s under the hood, to support VMs, bare-metal, and IoT devices (in the future). You could also deploy OpenModelZ on a existing kubernetes cluster.A request will be routed to the inference servers by the load balancer. And the autoscaler will scale the number of inference servers based on the workload. We provide a domain *.modelz.live
by default, with the help of a wildcard DNS server to support the public accessible subdomain for each deployment. You could also use your own domain.
You could check out the architecture documentation for more details.
Please checkout ROADMAP.
We welcome all kinds of contributions from the open-source community, individuals, and partners.
AI数字人视频创作平台
Keevx 一款开箱即用的AI数字人视频创作平台,广泛适用于电商广告、企业培训与社媒宣传,让全球企业与个人创作者无需拍摄剪辑,就能快速生成多语言、高质量的专业视频。
一站式AI创作平台
提供 AI 驱动的图片、视频生成及数字人等功能,助力创意创作
AI办公助手,复杂任务高效处理
AI办公助手,复杂任务高效处理。办公效率低?扣子空间AI助手支持播客生成、PPT制作、网页开发及报告写作,覆盖科研、商业、舆情等领域的专家Agent 7x24小时响应,生活工作无缝切换,提升50%效率!
AI辅助编程,代码自动修复
Trae是一种自适应的集成开发环境(IDE),通过自动化和多元协作改变开发流程。利用Trae,团队能够更快速、精确地编写和部署代码,从而提高编程效率和项目交付速度。Trae具备上下文感知和代码自动完成功能,是提升开发效率的理想工具。
AI小说写作助手,一站式润色、改写、扩写
蛙蛙写作—国内先进的AI写作平台,涵盖小说、学术、社交媒体等多场景。提供续写、改写、润色等功能,助力创作者高效优化写作流程。界面简洁,功能全面,适合各类写作者提升内容品质和工作效率。
全能AI智能助手,随时解答生活与工作的多样问题
问小白,由元石科技研发的AI智能助手,快速准确地解答各种生活和工作问题,包括但不限于搜索、规划和社交互动,帮助用户在日常生活中提高效率,轻松管理个人事务。
实时语音翻译/同声传译工具
Transly是一个多场景的AI大语言模型驱动的同声传译、专业翻译助手,它拥有超精准的音频识别翻译能力,几乎零延迟的使用体验和支持多国语言可以让你带它走遍全球,无论你是留学生、商务人士、韩剧美剧爱好者,还是出国游玩、多国会议、跨国追星等等,都可以满足你所有需要同传的场景需求,线上线下通用,扫除语言障碍,让全世界的语言交流不再有国界。
一键生成PPT和Word,让学习生活更轻松
讯飞智文是一个利用 AI 技术的项目,能够帮助用户生成 PPT 以及各类文档。无论是商业领域的市场分析报告、年度目标制定,还是学生群体的职业生涯规划、实习避坑指南,亦或是活动策划、旅游攻略等内容,它都能提供支持,帮助用户精准表达,轻松呈现各种信息。
深度推理能力全新升级,全面对标OpenAI o1
科大讯飞的星火大模型,支持语言理解、知识问答和文本创作等多功能,适用于多种 文件和业务场景,提升办公和日常生活的效率。讯飞星火是一个提供丰富智能服务的平台,涵盖科技资讯、图像创作、写作辅助、编程解答、科研文献解读等功能,能为不同需求的用户提供便捷高效的帮助,助力用户轻松获取信息、解决问题,满足多样化使用场景。
一种基于大语言模型的高效单流解耦语音令牌文本到语音合成模型
Spark-TTS 是一个基于 PyTorch 的开源文本到语音合成项目,由多个知名机构联合参与。该项目提供了高效的 LLM(大语言模型)驱动的语音合成方案,支持语音克隆和语音创建功能,可通过命令行界面(CLI)和 Web UI 两种方式使用。用户可以根据需求调整语音的性别、音高、速度等参数,生成高质量的语音。该项目适用于多种场景,如有声读物制作、智能语音助手开发等。
最新AI工具、AI资讯
独家AI资源、AI项目落地
微信扫一扫关注公众号