Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Pure Rust Inference Engine
| Date | Stars |
|---|---|
| 2026-07-31 | 622 |
| 2026-08-06 | 629 |
Today
+7 stars today
This week
— stars this week
This month
— stars this month
Momentum
28.0
growth rate 0.00%/day
<p align="center">
<img src="assets/logo.svg" alt="Atlas Inference Engine" width="640" />
</p>
<p align="center">
<h1 align="center">Atlas Inference Engine</h1>
<p align="center">
<strong>Pure Rust LLM Inference</strong><br>
<em>Universal Inference At Unimaginable Speeds</em>
</p>
<p align="center">
<img alt="NVIDIA" src="https://img.shields.io/badge/NVIDIA-76B900?style=flat-square&logo=nvidia&logoColor=white">
<img alt="AMD" src="https://img.shields.io/badge/AMD-ED1C24?style=flat-square&logo=amd&logoColor=white">
<img alt="Intel" src="https://img.shields.io/badge/Intel-0071C5?style=flat-square&logo=intel&logoColor=white">
</p>
<p align="center">
<a href="LICENSE"><img alt="License: AGPLv3" src="https://img.shields.io/badge/license-AGPLv3-yellow?style=flat-square"></a>
<a href="#quick-start"><img alt="Pure Rust" src="https://img.shields.io/badge/runtime-pure%20Rust-orange?style=flat-square"></a>
<a href="https://hub.docker.com/r/avarok/atlas-gb10"><img alt="Docker Hub" src="https://img.shields.io/badge/Docker%20Hub-avarok%2Fatlas--gb10-2496ED?style=flat-square&logo=docker&logoColor=white"></a>
<a href="https://discord.gg/6vDbKaKrKD"><img alt="Discord" src="https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fdiscord.com%2Fapi%2Fv10%2Finvites%2F6vDbKaKrKD%3Fwith_counts%3Dtrue&query=%24.approximate_member_count&label=discord&suffix=%20members&style=flat-square&logo=discord&logoColor=white&color=5865F2"></a>
</p>
</p>
<p align="center">
<a href="assets/atlas-demo.mp4"><img alt="Atlas demo — click for full-quality MP4" src="assets/atlas-demo.gif" width="820" /></a>
</p>
<p align="center">
<a href="#quick-start"><img alt="Quick Start — under 2 minutes" src="https://img.shields.io/badge/%E2%9A%A1%20Quick%20Start%20%E2%80%94%20%3C%202%20min-2EA44F?style=for-the-badge&logo=docker&logoColor=white"></a>
<a href="https://atlasinference.io"><img alt="atlasinference.io" src="https://img.shields.io/badge/%F0%9F%8C%90%20atlasinference.io-F48C06?style=for-the-badge"></a>
<a href="https://x.com/AIshaqui81766/status/2052121270506930276"><img alt="Launch announcement on X" src="https://img.shields.io/badge/%F0%9D%95%8F%20Launch%20Announcement-000000?style=for-the-badge&logo=x&logoColor=white"></a>
</p>
---
## 📑 Table of Contents
- [🧭 Philosophy](#philosophy)
- [🏛️ Architecture](#architecture)
- [📦 What We Ship Today](#models)
- [⚡ Performance](#performance)
- [🗜️ KV Cache Quantization](#kv-cache)
- [🚀 Quick Start](#quick-start)
- [🔬 Kernel Debugging](#debugging)
- [🔌 Adding a New Hardware Target](#new-hardware)
- [🧬 Adding a New Model](#new-model)
- [📚 Citations](#citations)
- [⚖️ License and Enterprise Edition](#license)
---
<a id="philosophy"></a>
## 🧭 Philosophy
The foundation of any given field of science is philosophy. It is that which inspires direction, structure, and mission.
Atlas began as a solution to widely known problem in using other (python) inference engines built by data scientists: the code was steeped in a poly codebase with an ever shifting ecosystem of dependencies, patches, and cross-dependencies. One day your workaround for running a model works, the next day you have to update to a nightly branch of several dependencies and inject a new workaround. This is not how you build a software ecosystem; that's how you build a proof of concept. We thank the great and hard work data scientists made in proving LLMs can revolutionize our world, its economy, and how it challenges us to higher epochs. Now, the software engineers take the torch to turn a proof of concept into something that is designed to withstand the test of time.
### Main Objective
Similar to how llama.cpp was built with the intent to prove you don't need $10000-$100000 GPUs to run LLMs, Atlas is built with the intent to consistently force the narrative that as hardware continues to advance, we should not have to pay premium Cloud API prices for inference. Atlas, by virtue of itExcerpt of 35,668 characters
Read on GitHub
99
24
15
13
9
4
4
4
2
2
1
1
1
1
1
1
1
1
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:e3f3a4e5f522d492, topic:llm-inference, desc:inference engine
matched fp:e3f3a4e5f522d492, topic:cuda