Artificial Intelligence tutorial - IT technology blog

Configuring Speculative Decoding with vLLM on Linux: Speed Up LLM Inference 2–3x Without Sacrificing Accuracy

Speculative Decoding is a technique that speeds up LLM inference by 2–3x by using a small draft model to predict multiple tokens ahead, then verifying them with the target model in a single forward pass. This guide covers configuration with vLLM on Linux — from a 5-minute quick start to EAGLE, ngram lookup, and tips for choosing the right draft model for production.
Database tutorial - IT technology blog

Getting Started with ChromaDB: The Open-Source Vector Database for Building AI Agent Knowledge Systems

ChromaDB is an open-source vector database for semantic storage and search — lightweight enough to run locally, powerful enough to serve as the foundation for RAG systems and AI Agents. This guide walks through installation, document indexing, semantic search queries, and Docker deployment with practical, step-by-step examples.