News for hackers. Stuff that matters.
Re:Life of an inference request (vLLM V1): How LLMs are serv... by animan on Saturday June 28, 2025 @08:11PM (#44409247)
That snippet is trying to say that you can calculate KV for all the input tokens at once, and you don't need to loop over them since you have them all available.

Instead for decode, you need to sequentially generate each token.

There are no comments on this comment yet.