From "token" to "MoE": the LLM glossary in dependency order

TL;DR — A glossary to actually understand the terms you hit when reading about LLMs: token, embedding, attention, KV cache, GQA, MoE, quantization and the rest. But not alphabetical — in dependency order : every entry uses only concepts already explained above, so if you read it start to finish,...

Source: [Dev.to](https://dev.to/mojalab/from-token-to-moe-the-llm-glossary-in-dependency-order-2pjf)