Unverified50% confidenceFactExact time
支持128K上下文的70B参数模型的KV Cache满负荷时可能需要数百GB显存，超过单张H100的80GB显存容量
1
Sources
50%
Confidence
Long-term
Relevance
7/17/2026
First Seen
Sources
Related Claims
Unverified100万Token在FP16精度下仅KV Cache一项即可消耗数百GB显存，远超单张A100/H100的80GB容量上限85% similarUnverified70B级别的模型即便经过量化，往往也需要40GB以上显存或多卡配置82% similarUnverified对于70B参数的模型，8K上下文的KV Cache可能额外占用数GB显存82% similarUnverified数千亿参数模型处理128K上下文窗口时，KV Cache可能占据数十GB显存80% similarUnverified以LLaMA-2 70B为例，处理4096 token上下文、批量大小32时，KV Cache可消耗超过80GB显存79% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/547421API
curl https://kongchang.com/api/v1/knowledge/claims/547421MCP
get_claim(id=547421)