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
- Challenges associated with cloud LLMs: data retention, input usage for training, and cross-border jurisdiction issues.
- Ollama architecture: encompassing the model server, registry, and OpenAI-compatible API.
- Technical comparison with vLLM, llama.cpp, and Text Generation Inference.
- Review of model licensing terms for Llama, Mistral, Qwen, and Gemma.
Installation and Hardware Configuration
- Setting up Ollama on Linux with support for CUDA and ROCm.
- Implementing CPU-only fallbacks and AVX/AVX2 optimizations.
- Deploying via Docker and configuring persistent volume mappings.
- Configuring multi-GPU environments and managing VRAM allocation strategies.
Model Management
- Fetching models from the Ollama registry using commands like 'ollama pull llama3'.
- Importing GGUF models from HuggingFace and TheBloke.
- Evaluating quantization levels such as Q4_K_M, Q5_K_M, and Q8_0 for optimal tradeoffs.
- Managing model switching and understanding concurrent model loading limits.
Custom Modelfiles
- Mastering Modelfile syntax: utilizing FROM, PARAMETER, SYSTEM, and TEMPLATE directives.
- Tuning parameters including temperature, top_p, and repeat_penalty.
- Engineering system prompts to define role-specific behavior.
- Creating custom models and publishing them to a local registry.
API Integration
- Utilizing the OpenAI-compatible /v1/chat/completions endpoint.
- Handling streaming responses and JSON mode operations.
- Integrating with LangChain, LlamaIndex, and custom application stacks.
- Implementing authentication and rate limiting via reverse proxies.
Performance Optimization
- Managing context window sizing and KV cache efficiency.
- Optimizing batch inference and parallel request handling.
- 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.
- Maintaining audit logs for prompts and completions.
- Verifying model provenance and hash integrity.
Requirements
- Intermediate proficiency in Linux and container administration.
- High-level understanding of machine learning 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 requirements that preclude cloud model usage.
- Government and defense teams needing air-gapped language model solutions.
