Skip to content

A universal scalable machine learning model deployment solution

License

Notifications You must be signed in to change notification settings

chen3933/djl-serving

 
 

Repository files navigation

DJL Serving

Overview

DJL Serving is a high performance universal stand-alone model serving solution powered by DJL. It takes a deep learning model, several models, or workflows and makes them available through an HTTP endpoint. It can serve the following model types out of the box:

  • PyTorch TorchScript model
  • TensorFlow SavedModel bundle
  • Apache MXNet model
  • ONNX model (CPU)
  • TensorRT model
  • Python script model

You can install extra extensions to enable the following models:

  • PaddlePaddle model
  • TFLite model
  • XGBoost model
  • LightGBM model
  • Sentencepiece model
  • fastText/BlazingText model

Key features

  • Performance - DJL serving running multithreading inference in a single JVM. Our benchmark shows DJL serving has higher throughput than most C++ model servers on the market
  • Ease of use - DJL serving can serve most models out of the box
  • Easy to extend - DJL serving plugins make it easy to add custom extensions
  • Auto-scale - DJL serving automatically scales up/down worker threads based on the load
  • Dynamic batching - DJL serving supports dynamic batching to increase throughput
  • Model versioning - DJL allows users to load different versions of a model on a single endpoint
  • Multi-engine support - DJL allows users to serve models from different engines at the same time

Installation

For macOS

brew install djl-serving

# Start djl-serving as service:
brew services start djl-serving

# Stop djl-serving service
brew services stop djl-serving

For Ubuntu

curl -O https://publish.djl.ai/djl-serving/djl-serving_0.23.0-1_all.deb
sudo dpkg -i djl-serving_0.23.0-1_all.deb

For Windows

We are considering to create a chocolatey package for Windows. For the time being, you can download djl-serving zip file from here.

curl -O https://publish.djl.ai/djl-serving/serving-0.23.0.zip
unzip serving-0.23.0.zip
# start djl-serving
serving-0.23.0\bin\serving.bat

Docker

You can also use docker to run DJL Serving:

docker run -itd -p 8080:8080 deepjavalibrary/djl-serving

Usage

DJL Serving can be started from the command line. To see examples, see the starting page.

More examples

More command line options

djl-serving --help
usage: djl-serving [OPTIONS]
 -f,--config-file <CONFIG-FILE>    Path to the configuration properties file.
 -h,--help                         Print this help.
 -m,--models <MODELS>              Models to be loaded at startup.
 -s,--model-store <MODELS-STORE>   Model store location where models can be loaded.
 -w,--workflows <WORKFLOWS>   Workflows to be loaded at startup.

See configuration for more details about defining models, model-store, and workflows.

REST API

DJL Serving uses a RESTful API for both inference and management calls.

When DJL Serving starts up, it has two web services:

  • Inference API - Used by clients to query the server and run models
  • Management API - Used to add, remove, and scale models on the server

By default, DJL Serving listens on port 8080 and is only accessible from localhost. Please see DJL Serving Configuration for how to enable access from a remote host.

Architecture

Details about how DJL Serving is implemented can be found in the architecture docs.

Plugin management

DJL Serving supports plugins, user can implement their own plugins to enrich DJL Serving features. See DJL Plugin Management for how to install plugins to DJL Serving.

Logging

you can set the logging level on the command-line adding a parameter for the JVM

-Dai.djl.logging.level={FATAL|ERROR|WARN|INFO|DEBUG|TRACE}

About

A universal scalable machine learning model deployment solution

Resources

License

Code of conduct

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Java 55.6%
  • Python 35.7%
  • Vue 4.9%
  • Dockerfile 1.5%
  • Shell 1.1%
  • JavaScript 0.9%
  • Other 0.3%