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
- Risks associated with cloud LLMs: data retention policies, training on user inputs, and foreign jurisdiction issues.
- Ollama architecture overview: model server components, registry functionality, and the OpenAI-compatible API layer.
- Comparative analysis with vLLM, llama.cpp, and Text Generation Inference.
- Model licensing terms for Llama, Mistral, Qwen, and Gemma.
Installation and Hardware Configuration
- Installing Ollama on Linux with CUDA and ROCm support enabled.
- Utilizing CPU-only fallback options and optimizing for AVX/AVX2 instructions.
- Docker deployment strategies and persistent volume mapping.
- Setting up multi-GPU environments and managing VRAM allocation strategies.
Model Management Techniques
- Retrieving models from the Ollama registry (e.g., running 'ollama pull llama3').
- Importing GGUF models sourced from HuggingFace and TheBloke.
- Evaluating trade-offs between quantization levels: Q4_K_M, Q5_K_M, and Q8_0.
- Managing model switching and understanding limits for concurrent model loading.
Developing Custom Modelfiles
- Syntax structure for 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 behaviors.
- Building and publishing custom models to a local registry.
API Integration Strategies
- Utilizing the OpenAI-compatible /v1/chat/completions endpoint.
- Implementing streaming responses and enabling JSON output mode.
- Connecting with LangChain, LlamaIndex, and bespoke applications.
- Managing authentication and rate limiting via reverse proxy configurations.
Performance Optimization Methods
- Configuring context window sizes and managing KV cache effectively.
- Handling batch inference and parallel request processing.
- Allocating CPU threads and maintaining NUMA awareness.
- Monitoring GPU utilization metrics and memory pressure levels.
Security and Compliance Measures
- Implementing network isolation for model serving endpoints.
- Establishing input filtering and output moderation pipelines.
- Setting up audit logging for prompts and generated completions.
- Verifying model provenance and validating file hashes.
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 data formats.
Target Audience
- AI engineers and developers seeking to replace cloud LLM APIs with local solutions.
- Organizations handling sensitive data that precludes the use of cloud models.
- Government and defense teams requiring air-gapped language model deployments.
14 Hours
