Unverified50% confidenceTradeoffExact time
在100K+ Token长上下文场景下KV Cache可能成为显存瓶颈，催生了GQA、PagedAttention等优化技术
1
Sources
50%
Confidence
Long-term
Relevance
7/22/2026
First Seen
Sources
Related Claims
UnverifiedvLLM compresses the KV Cache memory fragmentation rate from above 60% to near zero through PagedAttention technology, and can increase inference throughput by several times in high-concurrency scenarios.73% similarUnverifiedIn long-context scenarios (such as models with a 128K token window), the GPU memory occupied by the KV Cache may exceed that of the model weights themselves.72% similarUnverifiedvLLM的PagedAttention将KV Cache划分为固定大小物理块，通过块表实现地址映射，将碎片化率从60-80%降至不足4%，吞吐量提升可达24倍71% similarUnverified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71% similarVerifiedThe VRAM usage of KV Cache grows linearly with sequence length; for a 70-billion-parameter model using GQA, the KV Cache usage can reach tens of GB when processing 100,000 tokens.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/587517API
curl https://kongchang.com/api/v1/knowledge/claims/587517MCP
get_claim(id=587517)