PreSTO: Predictive Subtree Prefetching for Fast LLM Power Sampling
PreSTO speeds PowerMH LLM sampling by prefetching proposal subtrees without changing the transition kernel.
1 stories, newest first · one card per story
PreSTO speeds PowerMH LLM sampling by prefetching proposal subtrees without changing the transition kernel.
Today 1.6K readers · 2.5K views · 780 reads · all time 189K views