alt Hacker NewsPresumably it’s MoE and only needs to read a small fraction of the weights per token. Bonus points if you can get decent speculative decoding without becoming ALU-limited.
Presumably it’s MoE and only needs to read a small fraction of the weights per token. Bonus points if you can get decent speculative decoding without becoming ALU-limited.
Speculative decoding is not really worthwhile for sparsely-loaded models. You end up paying in both memory bandwith and compute (loading experts based on wrongly-predicted tokens) which leaves you worse off overall. It becomes viable (even for sparse MoE) once you're batching so widely that you end up having to load most of your total weights anyway.