similar idea, but the failure mode is better. a branch mispredict burns cycles. a bad guess here usually just means no bonus tokens.
https://arxiv.org/abs/2211.17192
As long as you're not bound on parallelism or bandwidth then it's "free", but if you're constrained on either resource then your lighter predictor model just needs to save you more cycles than it congests on average.
As long as you're not bound on parallelism or bandwidth then it's "free", but if you're constrained on either resource then your lighter predictor model just needs to save you more cycles than it congests on average.