Movatterモバイル変換


[0]ホーム

URL:


Skip to content

Navigation Menu

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
forked frommodular/max

The Mojo Programming Language

License

NotificationsYou must be signed in to change notification settings

dayanruben/mojo

 
 

Repository files navigation

Modular Logo

Welcome to MAX

Note: Mojo is included as a subdirectory in this repository

The Modular Accelerated Xecution (MAX) platformis an integrated suite of AI libraries, tools, and technologies that unifiescommonly fragmented AI deployment workflows. MAX accelerates time to marketfor the latest innovations by giving AI developers a single toolchain thatunlocks full programmability, unparalleled performance, and seamless hardware portability.

See here to get started with MAXand when you want to report issues or request features,please create a GitHub issue here.

TheDiscord community andour forum is the best place to shareyour experiences and chat with the team and other community members.

In theexamples directory,you will find code examples and Jupyter notebooks that show how to run inferencewith MAX.

Getting Started

MAX is available in both stable and nightly builds. To install either version,follow the guide tocreate a project withMagic.

Then clone this repository:

git clone https://github.com/modular/max.git

If you installed the stable build (v24.6), be sure you switch to thestable branch,because themain branch is for nightly releases and might not be compatiblewith stable builds:

git checkout stable

Running

MAX Pipelines

To show off the full power of MAX, aseries of end-to-end pipelines for common AI workloads(and more) are ready to run. As one example, this includes everything needed toself-hostthe Llama 3.1 text-generation model.All code is provided so that these pipelines can be customized, built upon, orlearned from.

Examples

In addition to the end-to-end pipelines, there are manyexamplesthat exercise various aspects of MAX. You can follow the instructions in theREADME for each example or notebook you want to run.

Notebooks

Check out thenotebooks examples for using MAX Engine🏎️ for models such as

Tutorials

Thetutorials directory contains the "finished" code fortutorials you can read atdocs.modular.com/max/tutorials.

Docker Container

The MAX container is our official Docker container for convenient MAX deployment.It includes the latest MAX version with GPU support, several AI libraries, andintegrates with orchestration tools like Kubernetes.

The MAX container image is available in theModular Docker Hub repository.

Contributing

Thanks for your interest in contributing to this repository!

We accept contributions to theMojo standard library.Please see theContribution Guide for instructions.

We are not accepting contributions for other parts of the repository.

We also welcome your bug reports. If you have a bug, please file an issuehere.

If you need support, theDiscordcommunity andour forum is the bestplace to share your experiences and chat with the team and othercommunity members.

License

This repository and its contributions are licensed under the Apache Licensev2.0 with LLVM Exceptions (see the LLVMLicense).MAX and Mojo usage and distribution are licensed under theMAX & Mojo Community License.

Third Party Licenses

You are entirely responsible for checking and validating the licenses ofthird parties (i.e. Huggingface) for related software and libraries that are downloaded.

About

The Mojo Programming Language

Resources

License

Code of conduct

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Mojo54.6%
  • Python21.0%
  • HTML15.5%
  • MDX8.5%
  • Shell0.3%
  • Jinja0.1%

[8]ページ先頭

©2009-2025 Movatter.jp