← Monday, October 12, 2026InferencePaper

PreSTO batches speculative proposals without changing PowerMH sampling

huggingface.co by Nan Jiang et al. Editor score 8/10

PreSTO batches prefetched Metropolis–Hastings proposals while preserving PowerMH's transition kernel, reporting median speedups of 1.71×, 1.91× and 2.33× across seven datasets and five base LLMs. The approach targets sequential sampling overhead without changing the sampler's behavior.

What

PreSTO accelerates PowerMH sampling by batching speculative proposals while leaving its Metropolis–Hastings transition kernel unchanged.

Method

Each model call generates proposals for a prefetched subtree in one batch, then follows the realized path using the original acceptance rule.

Why it matters

PreSTO reports median speedups of 1.71x on PowerMH, 1.91x on EntropyCut, and 2.33x on MultiTryMH across seven datasets and five base LLMs.

Read on huggingface.co → Code

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.