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.
Course Outline
AI Sovereignty and Local Deployment of LLMs
- Risks associated with cloud LLMs: data retention, input training, and foreign jurisdiction issues.
- Ollama architecture overview: model server, registry, and OpenAI-compatible API.
- Comparisons with vLLM, llama.cpp, and Text Generation Inference.
- Model licensing details for Llama, Mistral, Qwen, and Gemma.
Installation and Hardware Configuration
- Installing Ollama on Linux with CUDA and ROCm support.
- CPU-only fallback options and AVX/AVX2 optimisation techniques.
- Docker deployment methods and persistent volume mapping.
- Multi-GPU configuration and VRAM allocation strategies.
Model Management
- Downloading models from the Ollama registry: using commands like 'ollama pull llama3'.
- Importing GGUF models from HuggingFace and TheBloke repositories.
- Understanding quantization levels (Q4_K_M, Q5_K_M, Q8_0) and their trade-offs.
- Managing model switching and limits on concurrent model loading.
Custom Modelfiles
- Syntax for writing Modelfiles: utilizing FROM, PARAMETER, SYSTEM, and TEMPLATE directives.
- Tuning parameters such as temperature, top_p, and repeat_penalty.
- Engineering system prompts to define role-specific behaviours.
- Creating and publishing custom models to the local registry.
API Integration
- Utilizing the OpenAI-compatible /v1/chat/completions endpoint.
- Handling streaming responses and enabling JSON mode.
- Integrating with LangChain, LlamaIndex, and custom applications.
- Implementing authentication and rate limiting via reverse proxies.
Performance Optimisation
- Configuring context window size and managing KV cache.
- Conducting batch inference and handling parallel requests.
- Allocating CPU threads and ensuring NUMA awareness.
- Monitoring GPU utilization and managing memory pressure.
Security and Compliance
- Establishing network isolation for model serving endpoints.
- Implementing input filtering and output moderation pipelines.
- Maintaining audit logs for prompts and completions.
- Verifying model provenance and hash integrity.
Requirements
- Intermediate proficiency in Linux administration and container management.
- A high-level understanding of machine learning concepts and transformer models.
- Familiarity with REST APIs and JSON structures.
Audience
- AI engineers and developers seeking alternatives to cloud LLM APIs.
- Organisations bound by data sensitivity protocols that prohibit the use of cloud models.
- Government and defence teams requiring air-gapped language models for security.
14 Hours
