D-PACE: Dynamic Position-Aware Cross-Entropy for Parallel Speculative Drafting

摘要

Speculative decoding accelerates LLM inference by having a small drafter propose tokens that a larger target model verifies in parallel. Current SOTA diffusion-based parallel drafters such as dFlash predict the full $B$-token block in one forward pass, allowing deeper drafters and higher accepted length. However, across the field, from autoregressive tree drafters to parallel block drafters, training losses use fixed per-position weights that do not adapt to the drafter's current bottleneck position. We derive per-position training weights directly from the expected accepted block length, so that each position's weight reflects its actual contribution to acceptance. The resulting loss, D-PACE (Dynamic Position-Aware Cross-Entropy), automatically identifies where the block's acceptance bottleneck lies and shifts training signal there as the drafter improves. D-PACE consistently improves both wall-clock speedup and accepted length across diverse benchmarks and positions as a drop-in replacement with negligible training overhead and requires no changes to the drafter architecture or inference pipeline, making it broadly applicable to general model architectures.