发表机构
OPPO AI Center（OPPO人工智能中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对半自回归生成器DSpark的线性生成缺陷，提出父条件生成树（PCTree），通过为每个父节点生成多分支候选序列分配验证预算，在Qwen3系列模型及9个基准上显著提升了投机解码的推理加速效果。
AI 中文摘要
投机解码仅当生成的候选序列通过目标模型验证时，才能加速大语言模型（LLM）推理。半自回归生成器如DSpark通过一次骨干网络前向传播预测完整的token块，并使用轻量级马尔可夫头对其进行优化。然而，DSpark将该块解码为单链结构，因此早期的不匹配会使剩余后缀失效，限制了大生成块的优势。我们表明，DSpark已学习到的条件结构无需重新训练或额外的骨干网络前向传播，即可支持多个与父节点一致的候选序列。我们引入父条件生成树（PCTree），它使用预训练的马尔可夫头为每个具体父节点分别对备选子节点进行评分，并将固定的验证预算分配给最可能的路径。这将DSpark的线性生成转换为树结构，同时保留其单次并行骨干网络。在Qwen3-{4B,8B,14B}和9个基准测试中，当B=7时，与匹配的DSpark相比，PCTree相对于自回归（AR）解码的加速增益范围为3.1%至29.5%。在Qwen3-4B GSM8K且B=16时，PCTree将平均接受长度从9.41提升至11.16，三次运行的平均AR加速从6.14×提升至6.60×。这些结果表明，父条件分支可通过仅改变推理方式，将半自回归生成器中已存在的条件能力转化为端到端推理增益。
英文摘要
Speculative decoding accelerates LLM inference only when drafted continuations survive target-model verification. Semi-autoregressive drafters such as DSpark predict an entire token block with one backbone forward and refine it with a lightweight Markov head. However, DSpark decodes this block as a single chain, so an early mismatch invalidates the remaining suffix and limits the benefit of large draft blocks. We show that the conditional structure already learned by DSpark can support multiple parent-consistent continuations without retraining or additional backbone passes. We introduce Parent-Conditioned Drafting Tree (PCTree), which uses the pretrained Markov head to score alternative children separately for each concrete parent and allocates a fixed verification budget to the most probable paths. This converts DSpark's linear draft into a tree while preserving its one-pass parallel backbone. Across Qwen3-{4B,8B,14B} and nine benchmarks, at $B{=}7$, measured speedup gains over autoregressive (AR) decoding, relative to matched DSpark, range from $3.1\%$ to $29.5\%$. On Qwen3-4B GSM8K at $B{=}16$, PCTree increases mean acceptance length from $9.41$ to $11.16$ and three-run mean AR speedup from $6.14{\times}$ to $6.60{\times}$. These show that parent-conditioned branching can turn conditional capacity already present in a semi-autoregressive drafter into end-to-end inference gains through an inference-only change.
