JupyterLab Overview
JupyterLab in Armada Bridge's AI Studio provides interactive notebook environments where tenant users can write code, analyze data, and develop machine learning models — with direct access to GPU, CPU, or MIG (Multi-Instance GPU) resources provisioned by the Tenant Admin.
What You Can Do
- Run Python notebooks on GPU, CPU, or MIG environments
- Develop and test ML models with access to hardware resources
- Verify GPU and CPU utilization with built-in scripts
- Work in isolated, per-user environments within your tenant
Server Profiles
When adding a JupyterHub server, choose the profile that matches your workload:
| Profile | Resources | Use case |
|---|---|---|
| Environment with GPU access | Full GPU | ML training, CUDA, deep learning |
| Environment with CPU | CPU only | Data analysis, scripting, light computation |
| Environment with MIG GPU access | GPU partition | Workloads that need a fraction of a GPU |
Prerequisites
Before using JupyterLab:
- A JupyterHub cluster must exist — created by the Tenant Admin using the JupyterHub with KAI Scheduler cluster template
- You must have a tenant user account created by the Tenant Admin
- For MIG environments, the Tenant Admin must have configured a MIG profile
In This Section
- Create and Access Workspace — Authenticate and create GPU, CPU, or MIG JupyterHub servers
- Manage API Keys — Create and manage JupyterHub API keys