Skip to main content

AIVM: secure infrastructure for running MLaaS.

Project description

Nillion AIVM

AIVM is a framework designed for private inference using cryptographic protocols. This project allows you to run a development network (devnet) and perform private inference tasks using examples provided in the repository.

Table of Contents

Installing AIVM

Recommended Instalation

  1. Install on your existing OS python installation. Requires Python >=3.12:

    git clone https://github.com/NillionNetwork/aivm.git
    cd aivm
    
  2. Install dependencies:

    pip install .
    

If you are going to run the examples, do:

pip install ".[examples]"

Using Poetry

  1. Install Poetry (if not already installed):

    pip install poetry
    
  2. Clone the repository:

    git clone https://github.com/NillionNetwork/aivm.git
    cd aivm
    
  3. Install dependencies:

    poetry install
    
  4. Activate the virtual environment:

    poetry shell
    
  5. Install AIVM:

    poetry install
    

Using venv

  1. Clone the repository:

    git clone https://github.com/NillionNetwork/aivm.git
    cd aivm
    
  2. Create a virtual environment:

    python3 -m venv .venv
    
  3. Activate the virtual environment:

    On Linux/macOS:

    source .venv/bin/activate
    

    On Windows:

    .\venv\Scripts\activate
    
  4. Install the package:

    pip install .
    

Running AIVM

  1. Start the AIVM devnet:

    aivm-devnet
    
  2. Open the provided Jupyter notebook examples/getting-started.ipynb to run private inference examples on AIVM.

  3. After completing your tasks, terminate the devnet process by pressing CTRL+C.

Usage

For additional usage, refer to the examples provided in the examples folder, which demonstrates how to set up private inference workflows using AIVM.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

nillion_aivm-0.1.0.tar.gz (18.2 MB view details)

Uploaded Source

Built Distribution

nillion_aivm-0.1.0-py3-none-any.whl (18.4 MB view details)

Uploaded Python 3

File details

Details for the file nillion_aivm-0.1.0.tar.gz.

File metadata

  • Download URL: nillion_aivm-0.1.0.tar.gz
  • Upload date:
  • Size: 18.2 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.3 CPython/3.12.6 Linux/6.10.12-orbstack-00282-gd1783374c25e

File hashes

Hashes for nillion_aivm-0.1.0.tar.gz
Algorithm Hash digest
SHA256 9852694eedbbcdcaa82cf3988c7bda42a7166dcd388e4bbc915c8ed5e2d39644
MD5 3cf151f82de09113b700398fe23c8570
BLAKE2b-256 059123629d973391e4783abfcf69ffe3e4c0ef4aed3e38c96c35fc9e35e16016

See more details on using hashes here.

File details

Details for the file nillion_aivm-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: nillion_aivm-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 18.4 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.3 CPython/3.12.6 Linux/6.10.12-orbstack-00282-gd1783374c25e

File hashes

Hashes for nillion_aivm-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 8c87e1b6afa3a64804de954928891a49007a240130a26699df509544ce0751df
MD5 881825769f29b4571d5f9965bee249d9
BLAKE2b-256 054434a2e9ff340f0889186d9c45c2746b172d4e784473e936a09e176d954f4d

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page