Overview
CPU Servers (LiteLLM Routers)
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 10sXPU 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
|
||||||||
Cluster Models
| Model | Size | Runs On | Compatible Devices | Speed / Quality | API Key | Enabled | Actions |
|---|---|---|---|---|---|---|---|
|
🟠 GPU
🔵 CPU
🟣 NPU
|
/
/
—
|
|
|
|
Assign XPU Node to CPU Server
Node:
Set Pool Filters
Node:
Add Cluster Model
What are you trying to do?
Manually configure a model. It will auto-download to XPU nodes when Ollama starts.
Edit Model —
⚡ Cross-Device Benchmark
What benchmarks tell you
Run the same model on different nodes to compare real-world inference speed. Measures time-to-first-token (TTFT) and tokens/second.
Run Benchmark
Benchmark Results
| Node | Model | Compute | TTFT | Tok/sec | Total Time | Status | When | Actions |
|---|---|---|---|---|---|---|---|---|
Model Comparison
No comparison data available for this model.
🛡️ Remote Diagnostics
Nodes with Issues
No active alerts — all nodes are healthy! 🎉
Suggestion
Recent Diagnostic Logs
No diagnostic logs yet.
| Time | Node | Level | Message |
|---|---|---|---|
Send Message to Node
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 | bashWhat the script does
Registry Status
Firewall Setup
Open port 15029 to allow XPU contributors to connect:
sudo ufw allow 15029/tcp
sudo ufw reloadsudo firewall-cmd --permanent --add-port=15029/tcp
sudo firewall-cmd --reloadsudo 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