Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Duration 14 hours
Course Outline
Deployment Options
- Trade-offs between hosted APIs and self-hosting
- Patterns for on-premises, edge, and air-gapped environments
- Single model versus model portfolio strategies
- Comparing cost per decision
Hardware Sizing and Capacity
- Memory footprint relative to parameter count
- CPU-only versus GPU acceleration
- Planning for concurrency and throughput
- Allowing headroom for increases in task length
Serving Stacks
- vLLM and SGLang options
- llama.cpp and GGUF execution
- Ollama for local development
- Selecting based on the shape of the decision workload
Quantisation Without Losing Calibration
- Precision formats and memory efficiency
- Measuring quality and calibration loss
- Per-tensor and importance-aware variants
- Acceptance testing post-quantisation
Latency Engineering
- Median versus tail latency
- Latency growth with context length
- Warm start and model caching
- Batching multiple decision queries
Edge and Constrained Environments
- Running small decision models on CPU
- Apple Silicon and embedded deployments
- Offline operation and update strategies
- Distributing weights in air-gapped setups
Containerisation and Scaling
- Image design for model serving
- Volume and cache management
- Horizontal scaling and routing
- Resource limits and GPU sharing
Observability
- Request, latency, and error metrics
- Monitoring confidence distributions
- Tracking decision outcomes and escalations
- Alerting on calibration drift
Versioning and Rollout
- Versioning models and adapters
- Shadow and canary deployments
- Pinning model files for auditing
- Rollback procedures
Security and Multi-Tenancy
- Authentication and rate limiting
- Isolation of tenants for prompts and logs
- Network isolation and egress control
- Audit logging of decisions
Requirements
- Experience in Linux administration and containers.
- Familiarity with model inference servers and GPU management.
- Fundamental understanding of REST APIs, load balancing, and monitoring.
Audience
- MLOps and platform engineers managing inference infrastructure
- SRE teams supporting AI services
- AI engineers deploying decision models on-premises
- Architects designing air-gapped or regulated AI deployments
