alt Hacker News> maybe even learned prefetching for what the next experts will be
Experts are predicted by layer and the individual layer reads are quite small, so this is not really feasible. There's just not enough information to guide a prefetch.
Replies
snovv_crash • yesterday at 4:34 PM
Manually no. It would have to be learned, and making the expert selection predictable would need to be a training metric to minimize.
➕ show 1 reply
It's feasible to put the expert routing logic in a previous layer. People have done it: https://arxiv.org/abs/2507.20984