Unverified50% confidenceFactExact time
GQA (Grouped Query Attention) was introduced by Meta in LLaMA 2
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026
Sources
LFM2.5 Local Deployment Hands-On: An 8B Parameter Model That Outperforms GPT-o3s in Tool Calling
bilibiliAGI_Ananas6/1/2026
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1/469% similarUnverifiedMuse Glimmer采用Grouped Query Attention（GQA），仅有2个KV头，使KV Cache极为节省65% similarUnverifiedMeta开源的Llama Guard系列基于Llama架构微调，专门针对有害内容分类任务优化，参数量远小于完整生成模型54% similarUnverified由于基准饱和问题，社区开始转向GPQA和SWE-bench等更复杂的评测体系52% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/47932API
curl https://kongchang.com/api/v1/knowledge/claims/47932MCP
get_claim(id=47932)