Update README.md
Browse files
README.md
CHANGED
|
@@ -7,4 +7,39 @@ sdk: static
|
|
| 7 |
pinned: false
|
| 8 |
---
|
| 9 |
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
pinned: false
|
| 8 |
---
|
| 9 |
|
| 10 |
+
# Sbnb Linux
|
| 11 |
+
|
| 12 |
+
**Sbnb Linux** is a minimal, fast-booting Linux distro designed for AI/ML workloads on bare metal.
|
| 13 |
+
Built for full automation, GPU passthrough, and containerized workloads at scale.
|
| 14 |
+
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
### ⚙️ Purpose
|
| 18 |
+
|
| 19 |
+
Sbnb Linux enables you to **quickly and repeatably** put **bare-metal servers and GPUs** to work—perfect for:
|
| 20 |
+
|
| 21 |
+
- 🔁 Rapid LLM prototyping
|
| 22 |
+
- 🧠 Local multimodal inference
|
| 23 |
+
- 🧩 Running fleets of bare-metal servers — from **home labs** to **data centers**
|
| 24 |
+
|
| 25 |
+
Whether you're tinkering on a single GPU box or managing a rack of AI servers, Sbnb Linux scales with you.
|
| 26 |
+
|
| 27 |
+
---
|
| 28 |
+
|
| 29 |
+
### 🚀 Features
|
| 30 |
+
|
| 31 |
+
- 🧪 Run LLMs with **vLLM** or **SGLang** in seconds
|
| 32 |
+
- 🛠 Fully automated setup using **Ansible**
|
| 33 |
+
- 🔐 Secure remote access with **Tailscale**
|
| 34 |
+
- ⚡ Supports VFIO GPU passthrough with near-native performance
|
| 35 |
+
- 🐳 Container-native: ships with Docker and NVIDIA toolkit ready
|
| 36 |
+
|
| 37 |
+
---
|
| 38 |
+
|
| 39 |
+
### 📦 Repositories & Resources
|
| 40 |
+
|
| 41 |
+
- [GitHub Repository](https://github.com/sbnb-io/sbnb)
|
| 42 |
+
- [Hugging Face Organization](https://huggingface.co/sbnb)
|
| 43 |
+
- [Official Website](https://sbnb.io)
|
| 44 |
+
|
| 45 |
+
---
|