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
- Risks associated with cloud LLMs, including data retention, training on user inputs, and foreign jurisdiction issues.
- Ollama architecture covering the model server, registry, and OpenAI-compatible API.
- Comparison of Ollama with alternatives such as vLLM, llama.cpp, and Text Generation Inference.
- Licensing terms for models including Llama, Mistral, Qwen, and Gemma.
Installation and Hardware Configuration
- Installing Ollama on Linux with support for CUDA and ROCm.
- CPU-only fallback options and AVX/AVX2 optimizations.
- Docker deployment strategies and persistent volume mapping.
- Configuring multi-GPU environments and managing VRAM allocation.
Model Management
- Retrieving models from the Ollama registry, e.g., ollama pull llama3.
- Importing GGUF models from HuggingFace and TheBloke.
- Tradeoffs associated with quantization levels: Q4_K_M, Q5_K_M, and Q8_0.
- Model switching mechanisms and limits on concurrent model loading.
Custom Modelfiles
- Syntax for writing Modelfiles: FROM, PARAMETER, SYSTEM, TEMPLATE.
- Tuning parameters such as temperature, top_p, and repeat_penalty.
- Engineering system prompts for role-specific behaviors.
- Creating custom models and publishing them to the local registry.
API Integration
- Utilizing the OpenAI-compatible /v1/chat/completions endpoint.
- Handling streaming responses and enforcing JSON mode.
- Integrating with frameworks like LangChain, LlamaIndex, and custom applications.
- Implementing authentication and rate limiting via reverse proxies.
Performance Optimization
- Managing context window sizing and KV cache utilization.
- Optimizing batch inference and parallel request handling.
- CPU thread allocation strategies and NUMA awareness.
- Monitoring GPU utilization and memory pressure.
Security and Compliance
- Network isolation techniques for model serving endpoints.
- Implementing input filtering and output moderation pipelines.
- Maintaining audit logs of prompts and completions.
- Verifying model provenance and hashes.
Requirements
- Intermediate proficiency in Linux and container administration.
- High-level understanding of machine learning and transformer architectures.
- Knowledge of REST APIs and JSON structures.
Target Audience
- AI engineers and developers looking to substitute cloud LLM APIs.
- Organizations with data sensitivity constraints that preclude the use of cloud models.
- Government and defense teams requiring air-gapped language model capabilities.
