Feed Entities Podcasts Deep Dives Developers About

[KongchangAI]

Real-time AI knowledge base. Every claim is traceable to its source, with data freshness under 24 hours.

Powered by 240+ first-hand AI sources

Knowledge

Feed
Hot Entities
Podcasts

Developers

CLI
MCP Server
REST API
About

© 2026 KongchangAI. The freshest, most accurate AI knowledge

ConceptPrompt Caching

提示缓存

大语言模型API中的一项推理优化机制，通过在服务端复用多轮对话中不变前缀部分（系统提示、工具定义等）的KV Cache，避免重复计算，从而降低延迟与API调用成本

Source Articles

Claude Code v2.1.265更新详解：插件生态与稳定性优化Sep 11

Overview

Mentions: 1
Facts: 0
Related Entities: 0
Type: Concept

Citation

URI

/knowledge/%E6%8F%90%E7%A4%BA%E7%BC%93%E5%AD%98

API

/api/v1/knowledge/entity/%E6%8F%90%E7%A4%BA%E7%BC%93%E5%AD%98

MCP

get_entity("提示缓存")