https://github.com/bytedance/monolith

ByteDance's Recommendation System
https://github.com/bytedance/monolith

Last synced: 1 day ago
JSON representation

ByteDance's Recommendation System

• Host: GitHub
• URL: https://github.com/bytedance/monolith
• Owner: bytedance
• License: other
• Created: 2022-09-29T19:47:57.000Z (about 2 years ago)
• Default Branch: master
• Last Pushed: 2023-11-08T12:00:48.000Z (about 1 year ago)
• Last Synced: 2024-11-29T14:27:40.813Z (13 days ago)
• Language: Python
• Size: 23.5 MB
• Stars: 886
• Watchers: 49
• Forks: 125
• Open Issues: 11
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-github-star - monolith

README

        
 Monolith

## What is it?

[Monolith](https://arxiv.org/abs/2209.07663) is a deep learning framework for large scale recommendation modeling. It introduces two important features which are crucial for advanced recommendation system: 

* collisionless embedding tables guarantees unique represeantion for different id features

* real time training captures the latest hotspots and help users to discover new intersts rapidly

Monolith is built on the top of TensorFlow and supports batch/real-time training and serving.

## Discussion Group

### Join us at Discord

https://discord.gg/QYTDeKxGMX

## Quick start

### Build from source

Currently, we only support compilation on the Linux.

First, download bazel 3.1.0

```bash

wget https://github.com/bazelbuild/bazel/releases/download/3.1.0/bazel-3.1.0-installer-linux-x86_64.sh && \

  chmod +x bazel-3.1.0-installer-linux-x86_64.sh && \

  ./bazel-3.1.0-installer-linux-x86_64.sh && \

  rm bazel-3.1.0-installer-linux-x86_64.sh

```

Then, prepare a python environment

```bash

pip install -U --user pip numpy wheel packaging requests opt_einsum

pip install -U --user keras_preprocessing --no-deps

```

Finally, you can build any target in the monolith.

For example,

```bash

bazel run //monolith/native_training:demo --output_filter=IGNORE_LOGS

```

### Demo and tutorials

There are a tutorial in [markdown/demo](markdown/demo) on how to run distributed async training, and few guides on how to use the `MonolithModel` API [here](markdown).