Skip to main content

​
Dashboard Overview

The Bud Runtime dashboard provides a comprehensive interface for managing your AI workloads, models, and system resources.

​
Home Dashboard

The home dashboard displays:
  • Active model deployments
  • System resource utilization
  • Recent API requests
  • Performance metrics

​
Models Section

Navigate to the Models section to:
  • View deployed models
  • Deploy new models
  • Configure model parameters
  • Monitor model performance
Model Dashboard

​
API Management

Access API features:
  • Generate API keys
  • View API usage statistics
  • Configure rate limits
  • Test endpoints

​
Monitoring

Real-time monitoring includes:
  • GPU utilization
  • Memory usage
  • Request latency
  • Error rates
Performance Monitoring

​
Quick Actions

​
Deploy a Model

  1. Click “Deploy Model” from the dashboard
  2. Select model type and version
  3. Configure resources
  4. Click “Deploy”

​
Scale Deployments

  1. Navigate to the model details
  2. Adjust replica count
  3. Apply changes

​
View Logs

  1. Select a deployment
  2. Click “View Logs”
  3. Filter by time range or severity

​
Search and Filters

Use the search bar to:
  • Find specific models
  • Search API logs
  • Filter deployments by status

​
Keyboard Shortcuts

  • Ctrl/Cmd + K: Quick search
  • Ctrl/Cmd + /: Toggle help
  • G then M: Go to Models
  • G then A: Go to API

​
User Settings

Access user settings to:
  • Configure dashboard theme
  • Set notification preferences
  • Manage account settings
  • Export configurations

​
Tips for Efficient Navigation

  1. Use breadcrumbs to track your location
  2. Pin frequently used sections to the sidebar
  3. Customize the dashboard layout for your workflow
  4. Set up alerts for important events
For API integration details, see OpenAI Compatibility.