Git Product home page Git Product logo

inferrd's Introduction

Introduction

GitHub stars License

ML Deployment made simple, scalable and collaborative
The new open-source standard to deploy, monitor and secure Machine Learning services.

Inferrd is on a mission to make machine learning deployment a breeze.

  • Maintenance-free environments. Just drag and drop your models, and get an API.
  • Your data stays in your cloud. Have full control over where you send your data, and how it's processed.
  • No more security compliance process to go through as Inferrd is self-hosted.
  • No more pricing indexed on volume, as cloud-based solutions offer.

Quick start

Inferrd can be installed by installing docker and cloning this repository.

Make sure docker is installed on your inference server. You can install docker with:

curl -fsSL https://get.docker.com | sh

Then run the following commands to get started:

git clone https://github.com/inferrd/inferrd.git
cd inferrd
bash ./start.sh

Now visit http://localhost:8080 and login with email admin and password admin.

Features

  • Deploy form notebook: Use the Inferrd SDK to deploy from your notebook.
  • Wide framework support: Deploy TensorFlow, PyTorch, HuggingFace, ONNX, Scikit and XGBoost hassle free.
  • GPU support: GPU acceleration comes pre-configured out of the box.
  • Monitoring: Monitoring is available as soon as you make your first request. Prometheus monitoring is also available.
  • Versioning: Keep track of all the versions you deploy and rollback anytime.
  • Request logging: Inspect all requests coming into your model.

Community support

For general help using Inferrd, please refer to the official Inferrd documentation. For additional help, you can use one this repository to open issues.

Entreprise Support

Are you looking for support? Contact us.

Development

Run Inferrd locally, from source, to be able to make improvements, fix bugs etc.

Requirements:

  • Make sure you have Postgres v12 running on port 5432
  • Make sure Docker is running properly on your machine
  • Nomad installed. (brew install nomad on Mac for quick install)
  • Consul installed. (brew install consul on Mac for quick install)
  • Redis installed and running. (brew install redis on Mac for quick install)

Database setup: Create a user inferrd with password inferrd and a database called inferrd:

> psql
postgres=# create database inferrd;
postgres=# create user inferrd with encrypted password 'inferrd';
postgres=# grant all privileges on database inferrd to inferrd;

First, Nomad needs to be running on your machine:

$ yarn run nomad

Then, Consul needs to be running on your machine:

$ yarn run consul

Then, you will need to run the backend:

$ yarn # install all dependencies
$ yarn run dev # start Inferrd

Finally, start the frontend:

$ cd ui # the frontend is in the ui folder
$ yarn # install all dependencies
$ yarn run dev # start the frontend

Now visit http://localhost:8080 and login with email admin and password admin.

inferrd's People

Contributors

theo- avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.