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 LLM Deployment
- Identifying risks associated with cloud LLMs: data retention policies, usage for training inputs, and foreign jurisdiction implications.
- Understanding Ollama’s architecture: the model server, registry functionality, and OpenAI-compatible API structure.
- Comparing Ollama with alternatives such as vLLM, llama.cpp, and Text Generation Inference.
- Reviewing model licensing terms for Llama, Mistral, Qwen, and Gemma.
Installation and Hardware Configuration
- Installing Ollama on Linux systems with CUDA and ROCm support.
- Configuring CPU-only fallback options and enabling AVX/AVX2 optimizations.
- Deploying via Docker and mapping persistent volumes.
- Setting up multi-GPU environments and managing VRAM allocation strategies.
Model Management
- Pulling models from the Ollama registry using commands such as 'ollama pull llama3'.
- Importing GGUF format models from HuggingFace and TheBloke repositories.
- Evaluating quantization levels, including trade-offs between Q4_K_M, Q5_K_M, and Q8_0.
- Managing model switching and understanding limits on concurrent model loading.
Custom Modelfiles
- Writing Modelfile syntax using directives such as FROM, PARAMETER, SYSTEM, and TEMPLATE.
- Tuning key parameters like temperature, top_p, and repeat_penalty.
- Engineering system prompts to achieve role-specific model behavior.
- Building and publishing custom models to the local registry.
API Integration
- Utilizing the OpenAI-compatible /v1/chat/completions endpoint.
- Implementing streaming responses and enabling JSON output mode.
- Integrating local LLMs with frameworks like LangChain, LlamaIndex, and custom applications.
- Setting up authentication and rate limiting via reverse proxies.
Performance Optimization
- Managing context window sizes and KV cache efficiency.
- Handling batch inference and parallel requests.
- Allocating CPU threads and understanding NUMA (Non-Uniform Memory Access) awareness.
- Monitoring GPU utilization and memory pressure indicators.
Security and Compliance
- Establishing network isolation for model serving endpoints.
- Implementing input filtering and output moderation pipelines.
- Auditing logs of prompts and generated completions.
- Verifying model provenance through hash verification.
Requirements
- Intermediate-level knowledge of Linux and container administration.
- High-level understanding of machine learning concepts and transformer models.
- Familiarity with REST APIs and JSON data formats.
Target Audience
- AI engineers and developers seeking to move away from cloud LLM APIs.
- Organizations bound by strict data sensitivity regulations that prohibit the use of cloud-based models.
- Government and defense teams requiring air-gapped language model solutions.
14 Hours
Custom Corporate Training
Training solutions designed exclusively for businesses.
- Customized Content: We adapt the syllabus and practical exercises to the real goals and needs of your project.
- Flexible Schedule: Dates and times adapted to your team's agenda.
- Format: Online (live), In-company (at your offices), or Hybrid.
Price per private group, online live training, starting from 3200 € + VAT*
Contact us for an exact quote and to hear our latest promotions
