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
- Analysis of cloud LLM risks, including data retention, input usage for training, and foreign jurisdictional issues.
- Overview of Ollama’s architecture, covering its model server, registry, and OpenAI-compatible API.
- Comparative analysis of Ollama against vLLM, llama.cpp, and Text Generation Inference.
- Discussion on model licensing terms for Llama, Mistral, Qwen, and Gemma.
Installation and Hardware Configuration
- Steps for installing Ollama on Linux with support for CUDA and ROCm.
- Configuring CPU-only fallbacks and optimizing for AVX/AVX2 instructions.
- Deploying via Docker and mapping persistent volumes.
- Strategies for multi-GPU setups and VRAM allocation.
Model Management
- Retrieving models from the Ollama registry, such as using `ollama pull llama3`.
- Importing GGUF models from HuggingFace and TheBloke.
- Evaluating quantization levels like Q4_K_M, Q5_K_M, and Q8_0, including their tradeoffs.
- Managing model switching and understanding limits on concurrent model loading.
Creating Custom Modelfiles
- Syntax for writing Modelfiles, including FROM, PARAMETER, SYSTEM, and TEMPLATE directives.
- Tuning parameters such as temperature, top_p, and repeat_penalty.
- Engineering system prompts to achieve role-specific behaviors.
- Building and publishing custom models to a local registry.
API Integration
- Utilizing the OpenAI-compatible `/v1/chat/completions` endpoint.
- Implementing streaming responses and JSON mode.
- Integrating with frameworks like LangChain, LlamaIndex, and custom applications.
- Implementing authentication and rate limiting using reverse proxies.
Performance Optimization
- Managing context window sizing and KV cache efficiency.
- Handling batch inference and parallel request processing.
- Optimizing CPU thread allocation with NUMA awareness.
- Monitoring GPU utilization and memory pressure.
Security and Compliance
- Implementing network isolation for model serving endpoints.
- Establishing pipelines for input filtering and output moderation.
- Maintaining audit logs for prompts and completions.
- Verifying model provenance through hash checks.
Requirements
- Intermediate proficiency in Linux systems and container administration.
- A high-level understanding of machine learning principles and transformer architectures.
- Working knowledge of REST APIs and JSON data formats.
Target Audience
- AI engineers and developers looking to migrate away from cloud LLM APIs.
- Organizations with strict data sensitivity policies that preclude the use of cloud-based models.
- Government and defense units requiring air-gapped language model solutions.
