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 LLM Local Deployment
- Risks associated with cloud LLMs: data retention, training on user inputs, and foreign jurisdiction issues.
- Ollama architecture: model server, registry, and the OpenAI-compatible API.
- Comparison with alternatives such as vLLM, llama.cpp, and Text Generation Inference.
- Model licensing terms for Llama, Mistral, Qwen, and Gemma.
Installation and Hardware Setup
- Installing Ollama on Linux with CUDA and ROCm support.
- CPU-only fallback options and AVX/AVX2 optimization techniques.
- Docker deployment and persistent volume mapping strategies.
- Multi-GPU setup configurations and VRAM allocation methods.
Model Management
- Pulling models from the Ollama registry: example command ollama pull llama3.
- Importing GGUF models from HuggingFace and TheBloke repositories.
- Analyzing quantization levels: trade-offs between Q4_K_M, Q5_K_M, and Q8_0.
- Managing model switching and understanding 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 achieve role-specific behaviours.
- Creating and publishing custom models to a local registry.
API Integration
- Utilizing the OpenAI-compatible /v1/chat/completions endpoint.
- Implementing streaming responses and JSON mode functionalities.
- Integrating with LangChain, LlamaIndex, and custom applications.
- Managing authentication and rate limiting through reverse proxies.
Performance Optimization
- Sizing context windows and managing KV cache effectively.
- Handling batch inference and parallel request processing.
- Allocating CPU threads and ensuring NUMA awareness.
- Monitoring GPU utilization and memory pressure metrics.
Security and Compliance
- Implementing network isolation for model serving endpoints.
- Establishing input filtering and output moderation pipelines.
- Auditing logs of prompts and completions.
- Verifying model provenance and hash integrity.
Requirements
- Intermediate proficiency in Linux and container administration.
- A high-level understanding of machine learning concepts and transformer models.
- Familiarity with REST APIs and JSON structures.
Audience
- AI engineers and developers seeking to replace cloud LLM APIs.
- Organisations handling sensitive data that prohibits the use of cloud models.
- Government and defence teams requiring air-gapped language models.
14 Hours
