跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2608.30427 · v2

Ceiling-Clipped Acceptance Histograms Indicate Stranded Speed-up in Block-Diffusion Speculative Decoding

首次提交 2026-08-31 16:23
版本更新 2026-11-18 17:55
雷达观测 2026-11-19 15:04
arXiv ↗PDF ↗

摘要

Speculative decoding speeds up generation using an efficient draft model (drafter) to propose tokens that a target model verifies in one pass, preserving the target's output distribution. High-acceptance block-diffusion drafters, such as DFlash and DFlare, fill an entire block in one parallel pass. In many cycles, the target model accepts all draft tokens in the block, so the drafter exhausts its trained horizon before verification ever fails. We call this unrealized acceptance stranded speed-up. Evaluating a drafter by its per-prompt or per-cycle mean committed length alone hides this phenomenon, whereas the acceptance histogram exposes this bottleneck as a spike in the ceiling bin, the fraction of cycles that accept the entire block. We recommend reviewing the acceptance histogram before spending more training compute. Naively widening the block at inference could reduce acceptance for drafters with bidirectional attention, since, once the block outgrows its training size, the drafter's bidirectional attention shifts its distribution even at early positions, which empirically degrades acceptance there. We therefore post-train the drafter to a longer block with a short curriculum that emphasizes the newly exposed positions, a method we call DBloom. We continue training the pretrained DFlash and DFlare drafters at the original block size of 16, before expanding them to 24 (B16 to B24) on Qwen3-8B and Qwen3-4B. Compared to the original B16 drafters, this technique raises per-prompt committed length by up to +1.7 tokens and decode speed-up by a median of +10.2% versus +5.7% without the continuation. On high-ceiling benchmarks, the speed-up rises to +11.9%. On Gemma-4-12B-IT and GPT-OSS-20B, expansion also raises committed length on every benchmark. Against JetSpec, a tree drafter, DBloom has higher committed length by point estimate on every benchmark at tree budgets up to 64 nodes.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

本站首次收录为 v2,暂无更早版本可对照。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v2 · 2026-11-18 17:55 · 最新观测版本

Ceiling-Clipped Acceptance Histograms Indicate Stranded Speed-up in Block-Diffusion Speculative Decoding

Speculative decoding speeds up generation using an efficient draft model (drafter) to propose tokens that a target model verifies in one pass, preserving the target's output distribution. High-acceptance block-diffusion drafters, such as DFlash and DFlare, fill an entire block in one parallel pass. In many cycles, the target model accepts all draft tokens in the block, so the drafter exhausts its trained horizon before verification ever fails. We call this unrealized acceptance stranded speed-up. Evaluating a drafter by its per-prompt or per-cycle mean committed length alone hides this phenomenon, whereas the acceptance histogram exposes this bottleneck as a spike in the ceiling bin, the fraction of cycles that accept the entire block. We recommend reviewing the acceptance histogram before spending more training compute. Naively widening the block at inference could reduce acceptance for drafters with bidirectional attention, since, once the block outgrows its training size, the drafter's bidirectional attention shifts its distribution even at early positions, which empirically degrades acceptance there. We therefore post-train the drafter to a longer block with a short curriculum that emphasizes the newly exposed positions, a method we call DBloom. We continue training the pretrained DFlash and DFlare drafters at the original block size of 16, before expanding them to 24 (B16 to B24) on Qwen3-8B and Qwen3-4B. Compared to the original B16 drafters, this technique raises per-prompt committed length by up to +1.7 tokens and decode speed-up by a median of +10.2% versus +5.7% without the continuation. On high-ceiling benchmarks, the speed-up rises to +11.9%. On Gemma-4-12B-IT and GPT-OSS-20B, expansion also raises committed length on every benchmark. Against JetSpec, a tree drafter, DBloom has higher committed length by point estimate on every benchmark at tree budgets up to 64 nodes.

查看此版本解读 →查看此版本原文 ↗