Skip to main content

A tool for deploying and running AI models to Modal

Project description

PlumAI - Deploy and Run AI Models

Banner

PlumAI is a CLI tool that allows you to deploy and run AI models to Modal. It's completely free and open-source.

Table of Contents

Changelog

[Aug 10, 2024] - 🎉 Added support for Flux models.

Supported Platforms

PlumAI currently supports Linux, macOS, and Windows.

Installation

To install PlumAI, follow these steps:

  1. Verify System Requirements:
  • Python 3: Ensure Python 3 is installed on your system.
  1. Install PlumAI:
pip install plumai

This command installs PlumAI directly from the GitHub repository, including all necessary dependencies.

Usage

After installation, you can use PlumAI with the following commands:

Run a Flux model

plumai run [MODEL_NAME] [GPU_TYPE] [-f | --force]

# For example:
plumai run flux.1-dev A10G
  • MODEL_NAME: Specify the model name to run. Options are:

    • flux.1-dev (default)
    • flux.1-schnell
  • GPU_TYPE: Specify the GPU type to use. Options are:

    • T4 (not recommended)
    • A10G (default)
    • A100
    • L4
    • H100
  • f | --force: Use this option to force redeployment of the model, ignoring the cache. If the model has already been deployed and cached, using --force will trigger a new deployment process.

Troubleshooting

  • Git or Python3 not installed: If you encounter errors related to missing Git or Python3, install them using your system's package manager. For example, on Debian-based systems:
sudo apt-get update
sudo apt-get install -y git python3 python3-pip
  • Modal Setup Issues: If you encounter issues with Modal, ensure it is properly configured and installed. Refer to Modal's documentation for setup instructions.

License

This project is licensed under the MIT License.

Contributing

Contributions are welcome! Please submit issues or pull requests to the repository here.

Contact

For questions or support, please contact me via Twitter/X

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

plumai-0.1.11.tar.gz (9.6 kB view details)

Uploaded Source

Built Distribution

plumai-0.1.11-py3-none-any.whl (15.3 kB view details)

Uploaded Python 3

File details

Details for the file plumai-0.1.11.tar.gz.

File metadata

  • Download URL: plumai-0.1.11.tar.gz
  • Upload date:
  • Size: 9.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.9.19

File hashes

Hashes for plumai-0.1.11.tar.gz
Algorithm Hash digest
SHA256 f06e0a5d65f747697aa61678d7b3739afa54a506245b574bcb7ab68ecb665e56
MD5 55a904a13567049f25b3e01f57e6e823
BLAKE2b-256 6f0782aed605b5511e80f3a0e9322782012b897d47477bb1175eae273228e62f

See more details on using hashes here.

File details

Details for the file plumai-0.1.11-py3-none-any.whl.

File metadata

  • Download URL: plumai-0.1.11-py3-none-any.whl
  • Upload date:
  • Size: 15.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.9.19

File hashes

Hashes for plumai-0.1.11-py3-none-any.whl
Algorithm Hash digest
SHA256 d3279ef407898da67cb35023284fb67dc93b820633ea8fa1dd3e53790d049bcf
MD5 2231a25ef2acaea07e901312dc561eb4
BLAKE2b-256 11587d279c404e72cdb042ae5734e59253ad75de9398ce304694c2db0c9b940a

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