alt Hacker NewsSpeculative decoding! It makes inference a LOT faster.
Instead of generating tokens one at a time, you generate the second one as well, and then use speculative decoding on that second token (instead of having it be produced by a draft model like Qwen 0.6b). If the token is checked and is correct, then the 2nd token gets generated MUCH faster.
If it's wrong, you have to generate it again the normal way (a lot slower than just checking it). Usually, it's correct, so inference is a lot faster.
Replies
moffkalast • yesterday at 10:07 AM
Hmm but isn't the checking only required because the draft model is not the same model and can only speculate what the main one is thinking, hence the name? If the main model generates two tokens itself, then how can it be wrong about its own predictions?
➕ show 4 replies
Because then the second token only needs to be checked, not generated, as it’s already generated? And it’s much faster to generate multiple tokens at the same time than one at a time? Is that the idea?
I’m not an expert on LLMs, just a user.