← 返回列表

@teortaxesTex: This is pretty crazy ("Project status" under the abstract is also an insane detail). Further shrinking of V4 cache footprint to… 360 MB per ...

@teortaxesTex 3 信息等级 3 1 噪音/剔除；2 较弱；3 普通事实；4 重要行业动态；5 极重大事件。该分数是信息显著性，不是投资建议。 发布：2026-06-10T03:29 抓取：2026-06-10 05:19
🔗 原文链接
AI 算力
摘要

推特用户@teortaxesTex指出，某V4模型缓存占用进一步缩小至每1M上下文360 MB，相当于每token 360字节，接近原始明文限制的两个数量级。

客观事实
  • V4缓存占用缩小至每1M上下文360 MB
  • 每token缓存占用360字节

原文

This is pretty crazy ("Project status" under the abstract is also an insane detail). Further shrinking of V4 cache footprint to… 360 MB per 1M context? 360 bytes per token? Just 2 OOMs from the raw plaintext limit?
Calling CSA «conventional» is crazy work lmao.
@antirez !! https://t.co/X6AY2muwrW

likes: 46 | retweets: 2 | replies: 1 | views: 5604