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, including data retention, input training, and foreign jurisdiction.
- Ollama architecture: encompassing the model server, registry, and OpenAI-compatible API.
- Comparative analysis with vLLM, llama.cpp, and Text Generation Inference.
- Licensing considerations for models such as 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 deployment procedures and persistent volume mapping.
- Multi-GPU configuration and VRAM allocation techniques.
Model Management
- Fetching models from the Ollama registry: e.g., ollama pull llama3.
- Importing GGUF models from HuggingFace and TheBloke.
- Quantization levels: evaluating tradeoffs between Q4_K_M, Q5_K_M, and Q8_0.
- Model switching mechanics and concurrent model loading constraints.
Custom Modelfiles
- Modelfile syntax structure: FROM, PARAMETER, SYSTEM, and TEMPLATE directives.
- Adjusting temperature, top_p, and repeat_penalty parameters.
- System prompt engineering to define role-specific behaviors.
- Creating and publishing custom models to a local registry.
API Integration
- Utilizing the OpenAI-compatible /v1/chat/completions endpoint.
- Handling streaming responses and enabling JSON mode.
- Integration with LangChain, LlamaIndex, and proprietary applications.
- Implementing authentication and rate limiting via reverse proxies.
Performance Optimization
- Context window sizing and KV cache management techniques.
- Batch inference strategies and parallel request processing.
- CPU thread allocation and NUMA awareness for efficiency.
- Monitoring GPU utilization and memory pressure.
Security and Compliance
- Network isolation protocols for model serving endpoints.
- Implementing input filtering and output moderation pipelines.
- Audit logging of all prompts and generated completions.
- Ensuring model provenance and verifying hashes.
Requirements
- Intermediate proficiency in Linux and container administration.
- A high-level understanding of machine learning concepts and transformer architectures.
- Working knowledge of REST APIs and JSON data structures.
Target Audience
- AI engineers and developers seeking to migrate from cloud LLM APIs.
- Organizations with data sensitivity restrictions that preclude cloud model usage.
- Government and defense teams requiring air-gapped language model solutions.
