Unverified50% confidenceFactExact time
KV Cache only caches K and V but not Q, because Q is only used in the current step and discarded after use, whereas historical K and V are re-accessed at every subsequent step.
1
Sources
50%
Confidence
Long-term
Relevance
9/23/2026
First Seen
Sources
Related Entities
Related Claims
Unverified上下文越长，模型需要缓存的 KV Cache 越大，KV Cache 使模型生成新 Token 时无需重新计算所有历史 Token 的注意力权重74% similarUnverifiedKV Cache（键值缓存）用于避免自回归生成时对历史 token 的重复计算，但长上下文场景下预填充阶段需占用大量 HBM 显存带宽，拉长首 token 延迟（TTFT）73% similarVerifiedKV Cache avoids redundant computation by caching already-computed Key and Value matrices, and advanced techniques such as PagedAttention further optimize cache memory management efficiency.70% similarUnverifiedWith KV Cache, each round of Q projection only needs to compute a 1×D_k vector, whereas without caching, a full N×D_k matrix must be computed.70% similarUnverifiedThe disk caching mechanism persists already-computed KV Cache to storage media; when a subsequent request's prefix hits the cache, it can be reused directly, skipping redundant forward propagation.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/942619API
curl https://kongchang.com/api/v1/knowledge/claims/942619MCP
get_claim(id=942619)