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: data retention policies, potential training on user inputs, and foreign jurisdictional constraints.
- Ollama architecture: encompassing the model server, registry, and OpenAI-compatible API.
- 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 support for CUDA and ROCm.
- Implementing CPU-only fallbacks and AVX/AVX2 optimizations.
- Deploying via Docker and configuring persistent volume mappings.
- Configuring multi-GPU setups and strategies for 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 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.
- Creating and publishing custom models to the local registry.
API Integration
- Utilizing the OpenAI-compatible /v1/chat/completions endpoint.
- Handling streaming responses and JSON output modes.
- Integrating with LangChain, LlamaIndex, and custom applications.
- Implementing authentication and rate limiting via reverse proxies.
Performance Optimization
- Managing context window sizing and KV cache operations.
- Optimizing batch inference and handling parallel requests.
- Allocating CPU threads with 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 administration and container management.
- A high-level understanding of machine learning and transformer models.
- Familiarity with REST APIs and JSON data structures.
Audience
- AI engineers and developers looking to transition from cloud LLM APIs.
- Organizations where data sensitivity protocols restrict the use of cloud models.
- Government and defense teams requiring air-gapped language model solutions.
