Unverified50% confidenceFactExact time
GQA 通过让多个 Query 头共享同一组 Key-Value 头，在保持模型表达力的同时降低了 KV Cache 的显存占用
1
Sources
50%
Confidence
Long-term
Relevance
8/25/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedLLaMA 3 8B采用了分组查询注意力（GQA），将Key和Value的注意力头数量减少为Query头数的1/468% similarUnverifiedMuse Glimmer采用Grouped Query Attention（GQA），仅有2个KV头，使KV Cache极为节省66% similarUnverifiedKV缓存在推理阶段复用历史token的Key与Value矩阵，避免对已生成序列重复执行注意力计算65% similarVerified自注意力机制通过Query、Key、Value三个矩阵的点积运算，突破了RNN/LSTM因顺序计算导致的并行化瓶颈63% similarUnverifiedGQA (Grouped Query Attention) was introduced by Meta in LLaMA 257% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/798527API
curl https://kongchang.com/api/v1/knowledge/claims/798527MCP
get_claim(id=798527)