Metadata-Version: 2.1
Name: nebullvm
Version: 0.10.0
Description-Content-Type: text/markdown
License-File: LICENSE

<p align="center">
<br><br><br>
<a https://docs.nebuly.com/welcome/quick-start"><img src="https://user-images.githubusercontent.com/83510798/208247207-861541f0-b968-484c-8a0c-0fb110399c16.png" width="400px"></a>
<br><br><br>
</p>

<p align="center">
<b>A framework for building optimization modules to boost the performances of your AI systems</b>
</p>

<p align=center>
<a href="https://pypi.org/project/nebullvm/"><img src="https://badge.fury.io/py/nebullvm.svg"></a>
<a href="https://pypistats.org/packages/nebullvm"><img src="https://pepy.tech/badge/nebullvm"></a>
<a href="https://discord.gg/77d5kGSa8e"><img src="https://img.shields.io/badge/Discord-1.1k-blueviolet?logo=discord&amp;logoColor=white&style=round">
<a href="https://twitter.com/nebuly_ai"><img src="https://img.shields.io/twitter/url.svg?label=Follow%20%40nebuly_ai&style=social&url=https%3A%2F%2Ftwitter.com-nebuly_ai"></a>


</a>
  
---

**Documentation**: <a href="https://docs.nebuly.com/" target="_blank"> docs.nebuly.com/ </a>

---

`Nebullvm` is a framework for building the optimization modules needed to optimize the performances of your AI systems. The optimization modules are stack-agnostic and work with any library. They are designed to be easily integrated into your system, providing a quick and seamless boost to its performance. Simply plug and play to start realizing the benefits of optimized performance right away.

If you like the idea, give us a star to show your support for the project ⭐


## **What can this help with?**

There are multiple modules we actually provide built on top of the framework:

✅ [Speedster](https://github.com/nebuly-ai/nebuly/blob/main/optimization/speedster): Automatically apply the best set of SOTA optimization techniques to achieve the maximum inference speed-up on your hardware.

✅ [OpenAlphaTensor](https://github.com/nebuly-ai/nebuly/tree/main/optimization/open_alpha_tensor): Increase the computational performances of an AI model with custom-generated matrix multiplication algorithm fine-tuned for your specific hardware.

✅ [Forward-Forward](https://github.com/nebuly-ai/nebuly/tree/main/optimization/forward_forward): The Forward Forward algorithm is a method for training deep neural networks that replaces the backpropagation forward and backward passes with two forward passes.

## Next modules and roadmap
We are actively working on incorporating the following modules, as requested by members of our community, in upcoming releases:

- [ ]  [CloudSurfer](https://github.com/nebuly-ai/nebuly/blob/main/optimization/cloud_surfer): Automatically discover the optimal cloud configuration and hardware on AWS, GCP and Azure to run your AI models.
- [ ]  [OptiMate](https://github.com/nebuly-ai/nebuly/blob/main/optimizatione/optimate): Interactive tool guiding savvy users in achieving the best inference performance out of a given model / hardware setup.

## Contributing
As an open source project in a rapidly evolving field, we welcome contributions of all kinds, including new features, improved infrastructure, and better documentation. If you're interested in contributing, please see the [linked](https://docs.nebuly.com/contributions) page for more information on how to get involved.

---

<p align="center">
  <a href="https://discord.gg/RbeQMu886J">Join the community</a> |
  <a href="https://docs.nebuly.com/contributions/">Contribute to the library</a>
</p>
