Verified65% confidenceFactExact time
The size of the KV cache grows linearly with context length, and VRAM consumption increases significantly when processing longer texts.
3
Sources
65%
Confidence
Long-term
Relevance
8/26/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedKV缓存将已计算的Key-Value矩阵存储在显存中实现增量计算，代价是显存占用随序列长度线性增长80% similarUnverifiedKV缓存随上下文长度增加，显存占用可达总显存的60%以上77% similarUnverifiedGeneration throughput (tok/s) reflects decoding-phase efficiency and is affected by KV Cache size and memory bandwidth, with far lower sensitivity to input length than prefilling.77% similarVerifiedThe VRAM occupied by KV Cache grows linearly with sequence length.77% similarUnverifiedThe KV cache stores key-value pairs from Transformer attention computations and grows linearly with sequence length.76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/802146API
curl https://kongchang.com/api/v1/knowledge/claims/802146MCP
get_claim(id=802146)