#machine-learning #model #amazon-s3 #deep-learning #framework #tensorflow #thin

jams-core

jams-core provides thin abstraction around common machine learning and deep learning models, model stores like S3, Azure as well as databases like redis, dynamodb which can be used as real time feature stores. You can think of each component as a LEGO block which can be used to build a system depending on the requirements

23 releases

new 0.2.2 Jun 17, 2024
0.2.1 Jun 16, 2024
0.1.19 Jun 9, 2024

#722 in Machine learning

Download history 1216/week @ 2024-06-02 354/week @ 2024-06-09

1,570 downloads per month
Used in 3 crates

Apache-2.0

8MB
2.5K SLoC

Contains (Zip file, 15KB) pytorch-my_awesome_californiahousing_model.pt, (Zip file, 8KB) torch-my_awesome_penguin_model.pt

JAMS-CORE

This library crate is part of a wider project called J.A.M.S - Just Another Model Server. Please refer here.

This crate is the core building block of J.A.M.S. It provides a thin wrapper around the following models via FFI

  • Tensorflow
  • Torch
  • Catboost
  • LightGBM

This is still a work in process and is in very early stages.

Overview

Below diagram provides a high level overview of the crate

Alt text

Dependencies

~74MB
~1.5M SLoC