D-Cut prunes low-confidence draft suffixes across a batch of requests, using a confidence-based ranking and a profiled hardware cost model, to raise batched speculative decoding speedup from 1.26x to 1.65x.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
D-cut: Adaptive Verification Depth Pruning for Batched Speculative Decoding
D-Cut prunes low-confidence draft suffixes across a batch of requests, using a confidence-based ranking and a profiled hardware cost model, to raise batched speculative decoding speedup from 1.26x to 1.65x.