Overview
Total Nodes
Online Now
Total VRAM
GB
Available VRAM
GB
CPU Servers (LiteLLM Routers)
online
No CPU servers registered yet. Run
curl -fsSL https://rxpu.nixosoft.com/setup.sh | bash on your CPU server.
| Server | IP:Port | CPU | RAM | LiteLLM | Health | XPU Nodes | Status | Last Seen |
|---|---|---|---|---|---|---|---|---|
|
GB total
GB used
|
GPU Model Breakdown
| GPU Model | Count | Total VRAM |
|---|---|---|
| GB |
Online Nodes
Auto-refreshes every 10sNo nodes online
XPU Nodes
| Node Name | Owner | GPU Model | VRAM | Mode | IP:Port | Status | Last Heartbeat | Actions |
|---|---|---|---|---|---|---|---|---|
|
Assigned
Pool
Online
Offline
OS Platform
Driver Version
CUDA Version
Registered
Mode
Pool Min VRAM
Pool GPU Filter
API Key
Node ID
User ID
|
||||||||
No nodes match your filter
Cluster Models
| Model Name | Ollama Name | B2 Path | Size (GB) | Description | Enabled | Actions |
|---|---|---|---|---|---|---|
No cluster models configured. Click "Add Model" to add a model that will auto-download to XPU nodes.
Assign XPU Node to CPU Server
Node:
Set Pool Filters
Node:
Add Cluster Model
Configure a model that will auto-download to XPU nodes when Ollama starts.
Leave empty to use ollama pull only
Server Setup
One-Click Server Setup
Run this on any Linux CPU server. It installs LiteLLM, fetches all online XPU nodes from rxpu.nixosoft.com, and starts a unified OpenAI-compatible API endpoint on port 4000.
curl -fsSL https://rxpu.nixosoft.com/setup.sh | bash
Ubuntu 20.04+ / Debian 11+ / CentOS 8+
What the script does
Registry Status
✓ Healthy
✗ Unreachable
Checking...
Firewall Setup
Open port 15029 to allow XPU contributors to connect:
Ubuntu/Debian (UFW)
sudo ufw allow 15029/tcp
sudo ufw reloadCentOS/RHEL (firewalld)
sudo firewall-cmd --permanent --add-port=15029/tcp
sudo firewall-cmd --reloadDirect iptables
sudo iptables -A INPUT -p tcp --dport 15029 -j ACCEPTShare with XPU Contributors
Send this to people who want to contribute their XPU:
🖥️ RemoteXPU Registry
Registry URL: https://rxpu.nixosoft.com
Download the app: https://nixosoft.com/downloads
1. Download and install RemoteXPU
2. Launch it
3. Select "Join an existing cluster"
4. Paste the registry URL above
5. Sign in with Google shared-gpu-registry:
build: ./registry-service
container_name: shared-gpu-registry
restart: unless-stopped
ports:
- "15129:3456"
env_file:
- ./registry-service/.env
environment:
- PORT=3456Environment Variables
✓
✗
Settings
Current configuration loaded from environment variables. To modify, update the .env file and restart the service.
How to Update
1. SSH into the server hosting the Docker container
2. Edit the .env file in the registry-service directory
3. Restart the container:
docker compose up -d shared-gpu-registry