{"id":13633366,"url":"https://github.com/tensorchord/openmodelz","last_synced_at":"2025-06-21T11:08:28.666Z","repository":{"id":186690153,"uuid":"666033021","full_name":"tensorchord/openmodelz","owner":"tensorchord","description":"Autoscale LLM (vLLM, SGLang, LMDeploy) inferences on Kubernetes (and others)","archived":false,"fork":false,"pushed_at":"2023-11-03T06:33:25.000Z","size":1036,"stargazers_count":267,"open_issues_count":24,"forks_count":24,"subscribers_count":8,"default_branch":"main","last_synced_at":"2025-05-22T00:29:13.936Z","etag":null,"topics":["cluster-manager","hacktoberfest","inference","llm","llmops","mlops"],"latest_commit_sha":null,"homepage":"https://docs.open.modelz.ai","language":"Go","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/tensorchord.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2023-07-13T14:50:20.000Z","updated_at":"2025-05-21T09:19:54.000Z","dependencies_parsed_at":null,"dependency_job_id":"2dda9d47-efeb-4c85-8741-1e9124e55763","html_url":"https://github.com/tensorchord/openmodelz","commit_stats":null,"previous_names":["tensorchord/openmodelz"],"tags_count":28,"template":false,"template_full_name":null,"purl":"pkg:github/tensorchord/openmodelz","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tensorchord%2Fopenmodelz","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tensorchord%2Fopenmodelz/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tensorchord%2Fopenmodelz/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tensorchord%2Fopenmodelz/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/tensorchord","download_url":"https://codeload.github.com/tensorchord/openmodelz/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tensorchord%2Fopenmodelz/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":261110613,"owners_count":23111065,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["cluster-manager","hacktoberfest","inference","llm","llmops","mlops"],"created_at":"2024-08-01T23:00:35.128Z","updated_at":"2025-06-21T11:08:23.653Z","avatar_url":"https://github.com/tensorchord.png","language":"Go","funding_links":[],"categories":["Large Scale Deployment","Go"],"sub_categories":["ML Platforms"],"readme":"\u003cdiv align=\"center\"\u003e\n\n# OpenModelZ\n\n\u003c/div\u003e\n\n\u003cp align=center\u003e\n\u003ca href=\"https://discord.gg/KqswhpVgdU\"\u003e\u003cimg alt=\"discord invitation link\" src=\"https://dcbadge.vercel.app/api/server/KqswhpVgdU?style=flat\"\u003e\u003c/a\u003e\n\u003ca href=\"https://twitter.com/TensorChord\"\u003e\u003cimg src=\"https://img.shields.io/twitter/follow/tensorchord?style=social\" alt=\"trackgit-views\" /\u003e\u003c/a\u003e\n\u003ca href=\"https://docs.open.modelz.ai\"\u003e\u003cimg src=\"https://img.shields.io/badge/docs.open.modelz.ai-455946.svg?style=socail\u0026logo=googlechrome\u0026logoColor=white\" alt=\"docs\" /\u003e\u003c/a\u003e\n\u003ca href=\"https://github.com/tensorchord/openmodelz#contributors-\"\u003e\u003cimg alt=\"all-contributors\" src=\"https://img.shields.io/github/all-contributors/tensorchord/openmodelz/main\"\u003e\u003c/a\u003e\n\u003ca href=\"https://github.com/tensorchord/openmodelz/actions/workflows/CI.yaml\"\u003e\u003cimg alt=\"CI\" src=\"https://github.com/tensorchord/openmodelz/actions/workflows/CI.yaml/badge.svg\"\u003e\u003c/a\u003e\n\u003ca href=\"https://badge.fury.io/py/openmodelz\"\u003e\u003cimg src=\"https://badge.fury.io/py/openmodelz.svg\" alt=\"PyPI version\" height=\"20\"\u003e\u003c/a\u003e\n\u003ca href='https://coveralls.io/github/tensorchord/openmodelz'\u003e\u003cimg src='https://coveralls.io/repos/github/tensorchord/openmodelz/badge.svg' alt='Coverage Status' /\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n## What is OpenModelZ?\n\nOpenModelZ ( `mdz` ) is tool to deploy your models to any cluster (GCP, AWS, Lambda labs, your home lab, or even a single machine).\n\nGetting 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.\n\nYou 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.\n\n\u003cp align=center\u003e\n\u003cimg src=\"https://user-images.githubusercontent.com/5100735/260630222-46e26e54-50c6-43ba-b3ea-2e64dd276f87.png\" alt=\"OpenModelZ\" width=\"1000\"/\u003e\n\u003c/p\u003e\n\n## Benefits\n\nOpenModelZ provides the following features out-of-the-box:\n\n- 📈 **Auto-scaling from 0**: The number of inference servers could be scaled based on the workload. You could start from 0 and scale it up to 10+ replicas easily.\n- 📦 **Support any machine learning framework**: You could deploy any machine learning framework (e.g. [vLLM](https://github.com/vllm-project/vllm)/[triton-inference-server](https://github.com/triton-inference-server/server)/[mosec](https://github.com/mosecorg/mosec) etc.) with a single command. Besides, you could also deploy your own custom inference server.\n- 🔬 **Gradio/Streamlit/Jupyter support**: We provide a robust prototyping environment with support for [Gradio](https://gradio.app), [Streamlit](https://streamlit.io/), [jupyter](https://jupyter.org/) and so on. You could visualize your model's performance and debug it easily in the notebook, or deploy a web app for your model with a single command.\n- 🏃 **Start from a single machine to a cluster of machines**: You could start from a single machine and scale it up to a cluster of machines without any hassle, with a single command `mdz server start`.\n- 🚀 **Public accessible subdomain for each deployment** ( optional ) : We provision a separate subdomain for each deployment without any extra cost and effort, making each deployment easily accessible from the outside.\n\nOpenModelZ is the foundational component of the ModelZ platform available at [modelz.ai](https://modelz.ai).\n\n## How it works\n\nGet 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.\n\n```text\n$ mdz server start\n🚧 Creating the server...\n🚧 Initializing the load balancer...\n🚧 Initializing the GPU resource...\n🚧 Initializing the server...\n🚧 Waiting for the server to be ready...\n🐋 Checking if the server is running...\n🐳 The server is running at http://146.235.213.84.modelz.live\n🎉 You could set the environment variable to get started!\n\nexport MDZ_URL=http://146.235.213.84.modelz.live\n$ export MDZ_URL=http://146.235.213.84.modelz.live\n```\n\nThen you could deploy your model with a single command `mdz deploy` and get the endpoint:\n\n```\n$ mdz deploy --image modelzai/gradio-stable-diffusion:23.03 --name sdw --port 7860 --gpu 1\nInference sd is created\n$ mdz list\n NAME  ENDPOINT                                                 STATUS  INVOCATIONS  REPLICAS \n sdw   http://sdw-qh2n0y28ybqc36oc.146.235.213.84.modelz.live   Ready           174  1/1      \n       http://146.235.213.84.modelz.live/inference/sdw.default                                \n```\n\n## Quick Start 🚀\n\n### Install `mdz`\n\nYou can install OpenModelZ using the following command:\n\n```text copy\npip install openmodelz\n```\n\nYou could verify the installation by running the following command:\n\n```text copy\nmdz\n```\n\nOnce you've installed the `mdz` you can start deploying models and experimenting with them.\n\n### Bootstrap `mdz`\n\nIt'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.\n\n\u003e Notice: We may require the root permission to bootstrap the `mdz` server on port 80.\n\n```\n$ mdz server start\n🚧 Creating the server...\n🚧 Initializing the load balancer...\n🚧 Initializing the GPU resource...\n🚧 Initializing the server...\n🚧 Waiting for the server to be ready...\n🐋 Checking if the server is running...\nAgent:\n Version:       v0.0.13\n Build Date:    2023-07-19T09:12:55Z\n Git Commit:    84d0171640453e9272f78a63e621392e93ef6bbb\n Git State:     clean\n Go Version:    go1.19.10\n Compiler:      gc\n Platform:      linux/amd64\n🐳 The server is running at http://192.168.71.93.modelz.live\n🎉 You could set the environment variable to get started!\n\nexport MDZ_URL=http://192.168.71.93.modelz.live\n```\n\nThe 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.\n\n```bash\n# Provide the public IP as an argument\n$ mdz server start 1.2.3.4\n```\n\nYou could also specify the registry mirror to speed up the image pulling process. Here is an example:\n\n```bash /--mirror-endpoints/\n$ mdz server start --mirror-endpoints https://docker.mirrors.sjtug.sjtu.edu.cn\n```\n\n### Create your first UI-based deployment\n\nOnce 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.\n\n```text\n$ mdz deploy --image jupyter/minimal-notebook:lab-4.0.3 --name jupyter --port 8888 --command \"jupyter notebook --ip='*' --NotebookApp.token='' --NotebookApp.password=''\"\nInference jupyter is created\n$ mdz list\n NAME     ENDPOINT                                                   STATUS  INVOCATIONS  REPLICAS\n jupyter  http://jupyter-9pnxdkeb6jsfqkmq.192.168.71.93.modelz.live  Ready           488  1/1\n          http://192.168.71.93/inference/jupyter.default                                                                         \n```\n\nYou could access the deployment by visiting the endpoint URL. The endpoint will be automatically generated for each deployment with the following format: `\u003cname\u003e-\u003crandom-string\u003e.\u003cip\u003e.modelz.live`.\n\nIt 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. \n\n![jupyter notebook](./images/jupyter.png)\n\n### Create your first OpenAI compatible API server\n\nYou could also create API-based deployments. We will use [OpenAI compatible API server with Bloomz 560M](https://github.com/tensorchord/modelz-llm#run-the-self-hosted-api-server) as an example in this tutorial.\n\n```text\n$ mdz deploy --image modelzai/llm-bloomz-560m:23.07.4 --name simple-server\nInference simple-server is created\n$ mdz list\n NAME           ENDPOINT                                                         STATUS  INVOCATIONS  REPLICAS \n jupyter        http://jupyter-9pnxdkeb6jsfqkmq.192.168.71.93.modelz.live        Ready           488  1/1      \n                http://192.168.71.93/inference/jupyter.default                                                 \n simple-server  http://simple-server-lagn8m9m8648q6kx.192.168.71.93.modelz.live  Ready             0  1/1      \n                http://192.168.71.93/inference/simple-server.default                                           \n```\n\nYou 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.\n\n```python\nimport openai\nopenai.api_base=\"http://simple-server-lagn8m9m8648q6kx.192.168.71.93.modelz.live\"\nopenai.api_key=\"any\"\n\n# create a chat completion\nchat_completion = openai.ChatCompletion.create(model=\"bloomz\", messages=[\n    {\"role\": \"user\", \"content\": \"Who are you?\"},\n    {\"role\": \"assistant\", \"content\": \"I am a student\"},\n    {\"role\": \"user\", \"content\": \"What do you learn?\"},\n], max_tokens=100)\n```\n\n### Scale your deployment\n\nYou could scale your deployment by using the `mdz scale` command.\n\n```text /scale/\n$ mdz scale simple-server --replicas 3\n```\n\nThe requests will be load balanced between the replicas of your deployment. \n\nYou could also tell the `mdz` to **autoscale your deployment** based on the inflight requests. Please check out the [Autoscaling](https://docs.open.modelz.ai/deployment/autoscale) documentation for more details.\n\n### Debug your deployment\n\nSometimes you may want to debug your deployment. You could use the `mdz logs` command to get the logs of your deployment.\n\n```text /logs/\n$ mdz logs simple-server\nsimple-server-6756dd67ff-4bf4g: 10.42.0.1 - - [27/Jul/2023 02:32:16] \"GET / HTTP/1.1\" 200 -\nsimple-server-6756dd67ff-4bf4g: 10.42.0.1 - - [27/Jul/2023 02:32:16] \"GET / HTTP/1.1\" 200 -\nsimple-server-6756dd67ff-4bf4g: 10.42.0.1 - - [27/Jul/2023 02:32:17] \"GET / HTTP/1.1\" 200 -\n```\n\nYou 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.\n\n```text /exec/\n$ mdz exec simple-server ps\nPID   USER     TIME   COMMAND\n    1 root       0:00 /usr/bin/dumb-init /bin/sh -c python3 -m http.server 80\n    7 root       0:00 /bin/sh -c python3 -m http.server 80\n    8 root       0:00 python3 -m http.server 80\n    9 root       0:00 ps\n```\n\n```text /exec/\n$ mdz exec simple-server -ti bash\nbash-4.4# \n```\n\nOr you could port-forward the deployment to your local machine and debug it locally.\n\n```text /port-forward/\n$ mdz port-forward simple-server 7860\nForwarding inference simple-server to local port 7860\n```\n\n### Add more servers\n\nYou 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.\n\n```text /join/\n$ mdz server join \u003cinternal ip address of the previous server\u003e\n$ mdz server list\n NAME   PHASE  ALLOCATABLE      CAPACITY        \n node1  Ready  cpu: 16          cpu: 16         \n               mem: 32784748Ki  mem: 32784748Ki \n               gpu: 1           gpu: 1      \n node2  Ready  cpu: 16          cpu: 16         \n               mem: 32784748Ki  mem: 32784748Ki \n               gpu: 1           gpu: 1      \n```\n\n### Label your servers\n\nYou 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.\n\n```text /--node-labels gpu=true,type=nvidia-a100/\n$ mdz server label node3 gpu=true type=nvidia-a100\n$ mdz deploy ... --node-labels gpu=true,type=nvidia-a100\n```\n\n## Architecture\n\nOpenModelZ is inspired by the [k3s](https://github.com/k3s-io/k3s) and [OpenFaaS](https://github.com/openfaas), but designed specifically for machine learning deployment. We keep the core of the system **simple, and easy to extend**.\n\nYou 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.\n\n\u003cp align=center\u003e\n\u003cimg src=\"https://user-images.githubusercontent.com/5100735/260627792-2e89f6b8-006c-4807-84a3-29b6785af812.png\" alt=\"OpenModelZ\" width=\"500\"/\u003e\n\u003c/p\u003e\n\nOpenModelZ is composed of two components:\n\n- Data Plane: The data plane is responsible for the servers. You could use `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.\n- Control Plane: The control plane is responsible for the deployments. It manages the deployments and the underlying resources.\n\nA 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](https://github.com/cunnie/sslip.io) to support the public accessible subdomain for each deployment. You could also use your own domain.\n\nYou could check out the [architecture](https://docs.open.modelz.ai/architecture) documentation for more details.\n\n## Roadmap 🗂️\n\nPlease checkout [ROADMAP](https://docs.open.modelz.ai/community).\n\n## Contribute 😊\n\nWe welcome all kinds of contributions from the open-source community, individuals, and partners.\n\n- Join our [discord community](https://discord.gg/KqswhpVgdU)!\n\n## Contributors ✨\n\n\u003c!-- ALL-CONTRIBUTORS-LIST:START - Do not remove or modify this section --\u003e\n\u003c!-- prettier-ignore-start --\u003e\n\u003c!-- markdownlint-disable --\u003e\n\u003ctable\u003e\n  \u003ctbody\u003e\n    \u003ctr\u003e\n      \u003ctd align=\"center\" valign=\"top\" width=\"14.28%\"\u003e\u003ca href=\"https://github.com/gaocegege\"\u003e\u003cimg src=\"https://avatars.githubusercontent.com/u/5100735?v=4?s=70\" width=\"70px;\" alt=\"Ce Gao\"/\u003e\u003cbr /\u003e\u003csub\u003e\u003cb\u003eCe Gao\u003c/b\u003e\u003c/sub\u003e\u003c/a\u003e\u003cbr /\u003e\u003ca href=\"https://github.com/tensorchord/openmodelz/commits?author=gaocegege\" title=\"Code\"\u003e💻\u003c/a\u003e \u003ca href=\"https://github.com/tensorchord/openmodelz/pulls?q=is%3Apr+reviewed-by%3Agaocegege\" title=\"Reviewed Pull Requests\"\u003e👀\u003c/a\u003e \u003ca href=\"#tutorial-gaocegege\" title=\"Tutorials\"\u003e✅\u003c/a\u003e\u003c/td\u003e\n      \u003ctd align=\"center\" valign=\"top\" width=\"14.28%\"\u003e\u003ca href=\"https://github.com/VoVAllen\"\u003e\u003cimg src=\"https://avatars.githubusercontent.com/u/8686776?v=4?s=70\" width=\"70px;\" alt=\"Jinjing Zhou\"/\u003e\u003cbr /\u003e\u003csub\u003e\u003cb\u003eJinjing Zhou\u003c/b\u003e\u003c/sub\u003e\u003c/a\u003e\u003cbr /\u003e\u003ca href=\"#question-VoVAllen\" title=\"Answering Questions\"\u003e💬\u003c/a\u003e \u003ca href=\"https://github.com/tensorchord/openmodelz/issues?q=author%3AVoVAllen\" title=\"Bug reports\"\u003e🐛\u003c/a\u003e \u003ca href=\"#ideas-VoVAllen\" title=\"Ideas, Planning, \u0026 Feedback\"\u003e🤔\u003c/a\u003e\u003c/td\u003e\n      \u003ctd align=\"center\" valign=\"top\" width=\"14.28%\"\u003e\u003ca href=\"https://blog.mapotofu.org/\"\u003e\u003cimg src=\"https://avatars.githubusercontent.com/u/12974685?v=4?s=70\" width=\"70px;\" alt=\"Keming\"/\u003e\u003cbr /\u003e\u003csub\u003e\u003cb\u003eKeming\u003c/b\u003e\u003c/sub\u003e\u003c/a\u003e\u003cbr /\u003e\u003ca href=\"https://github.com/tensorchord/openmodelz/commits?author=kemingy\" title=\"Code\"\u003e💻\u003c/a\u003e \u003ca href=\"#design-kemingy\" title=\"Design\"\u003e🎨\u003c/a\u003e \u003ca href=\"#infra-kemingy\" title=\"Infrastructure (Hosting, Build-Tools, etc)\"\u003e🚇\u003c/a\u003e\u003c/td\u003e\n      \u003ctd align=\"center\" valign=\"top\" width=\"14.28%\"\u003e\u003ca href=\"http://manjusaka.itscoder.com/\"\u003e\u003cimg src=\"https://avatars.githubusercontent.com/u/7054676?v=4?s=70\" width=\"70px;\" alt=\"Nadeshiko Manju\"/\u003e\u003cbr /\u003e\u003csub\u003e\u003cb\u003eNadeshiko Manju\u003c/b\u003e\u003c/sub\u003e\u003c/a\u003e\u003cbr /\u003e\u003ca href=\"https://github.com/tensorchord/openmodelz/issues?q=author%3AZheaoli\" title=\"Bug reports\"\u003e🐛\u003c/a\u003e \u003ca href=\"#design-Zheaoli\" title=\"Design\"\u003e🎨\u003c/a\u003e \u003ca href=\"#ideas-Zheaoli\" title=\"Ideas, Planning, \u0026 Feedback\"\u003e🤔\u003c/a\u003e\u003c/td\u003e\n      \u003ctd align=\"center\" valign=\"top\" width=\"14.28%\"\u003e\u003ca href=\"https://github.com/tddschn\"\u003e\u003cimg src=\"https://avatars.githubusercontent.com/u/45612704?v=4?s=70\" width=\"70px;\" alt=\"Teddy Xinyuan Chen\"/\u003e\u003cbr /\u003e\u003csub\u003e\u003cb\u003eTeddy Xinyuan Chen\u003c/b\u003e\u003c/sub\u003e\u003c/a\u003e\u003cbr /\u003e\u003ca href=\"https://github.com/tensorchord/openmodelz/commits?author=tddschn\" title=\"Documentation\"\u003e📖\u003c/a\u003e\u003c/td\u003e\n      \u003ctd align=\"center\" valign=\"top\" width=\"14.28%\"\u003e\u003ca href=\"https://page.codespaper.com\"\u003e\u003cimg src=\"https://avatars.githubusercontent.com/u/3764335?v=4?s=70\" width=\"70px;\" alt=\"Wei Zhang\"/\u003e\u003cbr /\u003e\u003csub\u003e\u003cb\u003eWei Zhang\u003c/b\u003e\u003c/sub\u003e\u003c/a\u003e\u003cbr /\u003e\u003ca href=\"https://github.com/tensorchord/openmodelz/commits?author=zwpaper\" title=\"Code\"\u003e💻\u003c/a\u003e\u003c/td\u003e\n      \u003ctd align=\"center\" valign=\"top\" width=\"14.28%\"\u003e\u003ca href=\"https://xuanwo.io/\"\u003e\u003cimg src=\"https://avatars.githubusercontent.com/u/5351546?v=4?s=70\" width=\"70px;\" alt=\"Xuanwo\"/\u003e\u003cbr /\u003e\u003csub\u003e\u003cb\u003eXuanwo\u003c/b\u003e\u003c/sub\u003e\u003c/a\u003e\u003cbr /\u003e\u003ca href=\"#content-Xuanwo\" title=\"Content\"\u003e🖋\u003c/a\u003e \u003ca href=\"#design-Xuanwo\" title=\"Design\"\u003e🎨\u003c/a\u003e \u003ca href=\"#ideas-Xuanwo\" title=\"Ideas, Planning, \u0026 Feedback\"\u003e🤔\u003c/a\u003e\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n      \u003ctd align=\"center\" valign=\"top\" width=\"14.28%\"\u003e\u003ca href=\"https://github.com/cutecutecat\"\u003e\u003cimg src=\"https://avatars.githubusercontent.com/u/19801166?v=4?s=70\" width=\"70px;\" alt=\"cutecutecat\"/\u003e\u003cbr /\u003e\u003csub\u003e\u003cb\u003ecutecutecat\u003c/b\u003e\u003c/sub\u003e\u003c/a\u003e\u003cbr /\u003e\u003ca href=\"#ideas-cutecutecat\" title=\"Ideas, Planning, \u0026 Feedback\"\u003e🤔\u003c/a\u003e\u003c/td\u003e\n      \u003ctd align=\"center\" valign=\"top\" width=\"14.28%\"\u003e\u003ca href=\"https://xieydd.github.io/\"\u003e\u003cimg src=\"https://avatars.githubusercontent.com/u/20329697?v=4?s=70\" width=\"70px;\" alt=\"xieydd\"/\u003e\u003cbr /\u003e\u003csub\u003e\u003cb\u003exieydd\u003c/b\u003e\u003c/sub\u003e\u003c/a\u003e\u003cbr /\u003e\u003ca href=\"#ideas-xieydd\" title=\"Ideas, Planning, \u0026 Feedback\"\u003e🤔\u003c/a\u003e\u003c/td\u003e\n    \u003c/tr\u003e\n  \u003c/tbody\u003e\n\u003c/table\u003e\n\n\u003c!-- markdownlint-restore --\u003e\n\u003c!-- prettier-ignore-end --\u003e\n\n\u003c!-- ALL-CONTRIBUTORS-LIST:END --\u003e\n\n## Acknowledgements 🙏\n\n- [K3s](https://github.com/k3s-io/k3s) for the single control-plane binary and process.\n- [OpenFaaS](https://github.com/openfaas) for their work on serverless function services. It laid the foundation for OpenModelZ.\n- [sslip.io](https://github.com/cunnie/sslip.io) for the wildcard DNS service. It makes it possible to access the server from the outside world without any setup.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftensorchord%2Fopenmodelz","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftensorchord%2Fopenmodelz","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftensorchord%2Fopenmodelz/lists"}