Unverified50% confidenceFactExact time
RadixAttention 通过将 KV Cache 组织为前缀树结构，使具有相同前缀的多个请求共享同一份缓存
1
Sources
50%
Confidence
Long-term
Relevance
7/17/2026
First Seen
Sources
Related Claims
UnverifiedRadixAttention 引入全局共享 KV Cache 池，通过引用计数和 LRU 淘汰策略管理缓存生命周期，并在 Radix Tree 中执行最长前缀匹配75% similarUnverifiedSGLang's RadixAttention technology uses a radix tree structure to cache shared prompt prefixes across different requests, so when 100 users use the same system prompt, the KV Cache only needs to be computed once.74% similarUnverifiedSGLang的核心创新RadixAttention将KV缓存组织为前缀树结构，使具有公共前缀的多个请求能够共享缓存73% similarUnverifiedThe implementation of the semantic memory layer typically relies on vector databases (such as Chroma, Qdrant, and Pinecone) for vectorized storage and similarity retrieval, a technical approach known as RAG.62% similarUnverified语义缓存将历史请求转化为向量嵌入存储在向量数据库中，通过余弦相似度超过阈值时直接返回缓存结果，GPTCache已将该能力产品化59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/536620API
curl https://kongchang.com/api/v1/knowledge/claims/536620MCP
get_claim(id=536620)