Self-Cluster

Use your deployed MSP management API for management operations and its inference Gateway for model requests. Check the deployed version and required permissions. Example addresses are placeholders.

Register clusters, manage resources, and monitor infrastructure health.

The Self-Cluster module provides end-to-end cluster lifecycle management:

Cluster Management: Register Kubernetes clusters with the platform, probe connectivity, inspect node inventory, sync model assets, and run advanced diagnostics. Organize clusters into resource groups and assign them to team members for controlled access.

Observability: Monitor real-time resource utilization across services, nodes, and clusters. Track GPU, CPU, and memory metrics with historical trend charts. Inspect per-GPU details on individual nodes and monitor model serving performance with latency, throughput, and cache hit metrics.

Manage Clusters

Register clusters, assign resource groups, and manage access.

Learn More

Monitor Performance

Track resource utilization and model serving metrics in real time.

Learn More