Comment by zozbot234
4 hours ago
Ultimately it would amount to lazy-loading the model, but the parameters themselves would be fetched from the network as needed, which still decreases time-to-first-token. It's true that "expert" choices will span most of the model, regardless of any particular "subject" or "topic" choice, but if we simply care about time-to-first-token it's still a viable strategy.
Perhaps you could generate a few tokens before the entire model is downloaded, but since every token takes a potentially different "path" through an MoE model, you'd still need to wait for the entire download before getting deeper than a handful of tokens... which is not really a UX improvement imo.