AI & LLM Glossary Explains Core Engineering Terms

This article serves as a glossary for AI and LLM engineering terms, aimed at backend engineers. It defines core concepts like tokens, context windows, inference, and parameters, as well as specialized terms related to attention mechanisms such as LoRA, quantization, and the KV cache. The glossary explains these terms at a practical level, distinguishing them from research or marketing definitions, to aid in day-to-day work. AI

IMPACT Provides a foundational understanding of key AI and LLM engineering terms for practitioners.

RANK_REASON This is an explanatory article defining AI/LLM terminology, not a release or significant industry event.

Read on dev.to — LLM tag →

• attention
• context window
• inference
• KV cache
• LLM
• LoRA
• quantization
• Tokens
• transformers

• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →