Parallel drafts stop guessing alone: candidate rescoring lifts speculative decoding throughput and still beats the uncorrected drafter at 32 concurrent streams
A parallel diffusion drafter emits a whole block in one forward pass but each slot never sees which tokens earlier slots actually chose; a lightweight corrector that reads only the drafter's existing hidden states and logits scores adjacent candidates in parallel and re-selects left to right, giving the highest average throughput across four verifier backbones and ten benchmarks and staying ahead of the uncorrected drafter at 32 concurrent streams.