[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]

![_avichawla Avatar](https://lunarcrush.com/gi/w:24/cr:twitter::1175166450832687104.png) Avi Chawla [@_avichawla](/creator/twitter/_avichawla) on x 42.3K followers
Created: 2025-07-27 06:30:24 UTC

To understand KV caching, we must know how LLMs output tokens.

- Transformer produces hidden states for all tokens.
- Hidden states are projected to the vocab space.
- Logits of the last token are used to generate the next token.
- Repeat for subsequent tokens.

Check this👇

![](https://pbs.twimg.com/tweet_video_thumb/Gw2BkPmbcAAHzfL.jpg)

XXXXXX engagements

![Engagements Line Chart](https://lunarcrush.com/gi/w:600/p:tweet::1949356680871067925/c:line.svg)

**Related Topics**
[token](/topic/token)
[$avijo](/topic/$avijo)

[Post Link](https://x.com/_avichawla/status/1949356680871067925)