LLM knowledge that simply works

A curated, practical wiki for prompting, training, serving, and evaluating large language models.

Get started Learn more

↓

Background is customizable in docs/stylesheets/extra.css

PromptingPatterns, structure, and evaluation ModelsFamilies, features, and trade-offs TrainingSFT, DPO/RLHF, LoRA/QLoRA InferenceThroughput, latency, quantization EvaluationMetrics, robustness, safety AgentsTools, planning, memory InfraServing stacks and scaling AppsRAG, extraction, UX ResourcesDocs, papers, tools

Contribute

• Read the Style Guide: meta/style-guide.md
• Learn the taxonomy: meta/taxonomy.md
• Use the template: meta/templates/article.md

Prefer authoritative docs and peer-reviewed sources when possible. Date time-sensitive info (benchmarks, API behavior, etc.).