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
AI Sovereignty and Local LLM Deployment
- Risks associated with cloud LLMs: data retention, training on user inputs, and foreign jurisdiction.
- Ollama architecture: model server, registry, and OpenAI-compatible API.
- Comparative analysis with vLLM, llama.cpp, and Text Generation Inference.
- Model licensing terms for Llama, Mistral, Qwen, and Gemma.
Installation and Hardware Configuration
- Installing Ollama on Linux with support for CUDA and ROCm.
- CPU-only fallback mechanisms and AVX/AVX2 optimization strategies.
- Docker-based deployment and persistent volume mapping.
- Multi-GPU configurations and VRAM allocation tactics.
Model Management
- Retrieving models from the Ollama registry: ollama pull llama3.
- Importing GGUF models from HuggingFace and TheBloke.
- Trade-offs between quantization levels: Q4_K_M, Q5_K_M, and Q8_0.
- Model switching logic and limits on concurrent model loading.
Custom Modelfiles
- Syntax for Modelfiles: FROM, PARAMETER, SYSTEM, TEMPLATE.
- Tuning parameters including temperature, top_p, and repeat_penalty.
- System prompt engineering for specific role-based behaviors.
- Creating and publishing custom models to a local registry.
API Integration
- Utilizing the OpenAI-compatible /v1/chat/completions endpoint.
- Handling streaming responses and JSON mode.
- Integration with LangChain, LlamaIndex, and bespoke applications.
- Implementing authentication and rate limiting via reverse proxy.
Performance Optimization
- Sizing context windows and managing KV caches.
- Batch inference and parallel request processing.
- CPU thread allocation and NUMA topology awareness.
- Monitoring GPU utilization and memory pressure.
Security and Compliance
- Network isolation for model serving endpoints.
- Pipelines for input filtering and output moderation.
- Audit logging for prompts and completions.
- Model provenance tracking and hash verification.
Requirements
- Intermediate proficiency in Linux and container administration.
- A high-level understanding of machine learning and transformer architectures.
- Practical familiarity with REST APIs and JSON data structures.
Target Audience
- AI engineers and developers seeking to substitute cloud LLM APIs.
- Organizations with sensitive data constraints that prohibit cloud model usage.
- Government and defense units requiring air-gapped language model capabilities.
