Unverified50% confidenceFactExact time
Multi-Query Attention (MQA) lets all query heads share the same set of Key/Value heads, compressing the KV cache to 1/H of its original size (H being the number of heads).
1
Sources
50%
Confidence
Long-term
Relevance
11/8/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedMQA令所有查询头共享同一组Key-Value以压缩KV Cache78% similarVerifiedGrouped Query Attention (GQA) and Multi-Query Attention (MQA) reduce KV cache memory usage during inference by having multiple query heads share the same group of key/value heads, and are standard optimizations in models such as Llama 3 and Mistral.75% similarUnverifiedThe concept of KV Cache groups originates from techniques such as GQA (Grouped Query Attention), where multiple query heads share the same set of KV heads.74% similarUnverifiedSelf-attention maps the input sequence into three sets of vectors — Query Q, Key K, and Value V — computes the dot-product similarity between Q and K, normalizes the result via Softmax to obtain attention weights, and then uses those weights to aggregate the V vectors.73% similarUnverifiedGQA reduces the size of the KV Cache by having multiple Query heads share the same set of Key-Value heads.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1147319API
curl https://kongchang.com/api/v1/knowledge/claims/1147319MCP
get_claim(id=1147319)