Files
nexus/wiki/sources/llm-terms-framework.md

45 lines
1.4 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
---
title: "大模型相关术语框架总结"
type: source
tags: [LLM, MCP, Prompt, RAG, vLLM, Token]
date: 2025-12-20
---
## Source File
- [[raw/AI/大模型相关术语和框架总结LLM、MCP、Prompt、RAG、vLLM、Token、数据蒸馏.md]]
## Summary
- 核心主题:大模型核心术语和技术框架
- 问题域:大模型领域术语众多难以系统理解
- 方法/机制:图解化梳理各术语关系
- 结论/价值:构建完整的大模型技术知识体系
## Key Claims
- LLMLarge Language Model大模型≥1B参数
- Prompt输入给大模型的语句
- MCPModel Context Protocol标准化接口连接外部数据和工具
- AgentLLM+MCP=智能体大模型给出步骤实际执行需配合MCP
- RAGRetrieval Augmented Generation检索增强生成解决幻觉问题
- Embedding向量化计算词与词之间的距离
- vLLM高效推理框架KV Cache+连续批处理提升GPU利用率
- Token基本输入单元1英文字符≈0.3 token1中文字符≈0.6 token
## Key Concepts
- [[LLM]]:大语言模型
- [[MCP]]:模型上下文协议
- [[Agent]]:智能体
- [[RAG]]:检索增强生成
- [[Embedding]]:向量化
- [[vLLM]]高效LLM推理框架
- [[Token]]:大模型基本输入单元
## Key Entities
## Connections
- [[LLM]] ← uses ← [[Token]]
- [[LLM]] ← uses ← [[MCP]]
- [[Agent]] ← combines ← [[LLM]] + [[MCP]]
- [[RAG]] ← extends ← [[LLM]]
## Contradictions