Parallel Decoder Transformer: Model-Internal Parallel Decoding with Speculative Invariance via Note Conditioning

Abstract

Autoregressive decoding in Large Language Models (LLMs) is inherently sequential, creating a latency bottleneck that scales linearly with output length. While ``Decomposition-and-Fill'' methods like Skeleton-of-Thought attempt to parallelize generation via external orchestration, they suffer from \textit{coherence drift} due to the lack of cross-stream communication. In this work, we introduce the \textbf{Parallel Decoder Transformer (PDT)}, a parameter-efficient architecture that embeds coordination primitives directly into the inference process of a frozen pre-trained model. Instead of retraining the base model, PDT injects lightweight \textit{Speculative Note Conditioning (SNC)} adapters that allow parallel decoding streams to synchronize via a shared, dynamic latent space. We formulate coordination as a \textit{speculative consensus} problem, where sibling streams broadcast semantic ``notes'' to a global bus, gated by a learned verification head. We validate our approach on a 50,000-step curriculum using a frozen 20B-parameter backbone. Our results demonstrate that PDT achieves effective self-correction, reaching \textbf{77.8\% precision} in coverage prediction and recovering approximate serial semantics without modifying the trunk weights. This establishes PDT as a scalable, efficient alternative to full model fine-tuning for structured parallel generation.