Dedicated Deployment
Deploy AI models with isolated infrastructure and specific hardware configurations
Dedicated Deployments
Dedicated deployments in Unicron provide isolated infrastructure with specific hardware configurations for your AI workloads.
Benefits
Dedicated deployments are suited for:
- Production workloads with consistent traffic
- Applications requiring specific hardware (GPU/CPU configurations)
- Fine-grained control over scaling and resources
- Applications with specific compliance or isolation requirements
Creating a Dedicated Deployment
From the Marketplace
- Navigate to your workspace:
/workspace/{workspace-slug}
- Click on "Deployments" in the navigation menu
- Click "Create Deployment" button
- Select the "Marketplace" tab and filter for dedicated options
- Choose a service and configure your hardware specifications
Custom Service Deployment
- Navigate to your workspace:
/workspace/{workspace-slug}
- Click on "Deployments" in the navigation menu
- Click "Create Deployment" button
- Select the "Custom Services" tab
- Click "Deploy Custom Service"
- Select "Dedicated" as the deployment type
- Configure your dedicated deployment:
- Service name and description
- Docker image details
- Hardware specifications (CPU, memory, GPU)
- Region selection
- Advanced configuration options (network, storage)
Hardware Options
Dedicated deployments offer various hardware configurations:
- CPU-optimized instances (various core counts)
- GPU instances (NVIDIA A100, T4, etc.)
- Memory-optimized instances
- Custom hardware configurations
Pricing
Dedicated deployments use a consistent pricing model:
- Fixed hourly rate based on hardware specifications
- Predictable monthly costs
- No traffic-based cost fluctuations
Management Features
Dedicated deployments include additional management capabilities:
- Direct infrastructure access
- Custom scaling policies
- Reserved capacity options
- Hardware isolation guarantees
- Enhanced security options