SSD: Spatially Speculative Decoding Accelerates Autoregressive Image Generation
Autoregressive image models treat images as 1D token sequences, inheriting the next-token factorization of language models. This flattening discards a useful property of images: nearby tokens are correlated in two dimensions, not one. We introduce Spatially Speculative Decoding (SSD), an inference-time decoding framework that exploits this spatial structure. Rather than speculating only along the flattened sequence, SSD predicts both the adjacent horizontal token and the token directly below it, allowing multiple spatial directions to advance in parallel. This reduces the number of backbone forward evaluations and alleviates the memory bottleneck of autoregressive decoding. SSD accelerates image generation by up to 11.03x in wall-clock time while maintaining generation quality on DPG-Bench and GenEval. These results show that spatial structure provides a simple and effective source of parallelism for autoregressive image generation.
Code (0)
등록된 구현이 없습니다.
Tasks
Image GenerationSimilar Papers 제목 키워드 기반
Fast Inference of Visual Autoregressive Model with Adjacency-Adaptive Dynamical Draft Trees
Autoregressive (AR) image models achieve diffusion-level quality but suffer from sequential inference, requiring approximately 2,000 steps for a 576x576 image. Speculative decoding with draft trees accelerates LLMs yet u…
SJD-VP: Speculative Jacobi Decoding with Verification Prediction for Autoregressive Image Generation
Speculative Jacobi Decoding (SJD) has emerged as a promising method for accelerating autoregressive image generation. Despite its potential, existing SJD approaches often suffer from the low acceptance rate issue of spec…
Image GenerationAMUSD: Asynchronous Multi-Device Speculative Decoding for LLM Acceleration
Large language models typically generate tokens autoregressively, using each token as input for the next. Recent work on Speculative Decoding has sought to accelerate this process by employing a smaller, faster draft mod…
Scaling LLM Speculative Decoding: Non-Autoregressive Forecasting in Large-Batch Scenarios
Speculative decoding accelerates LLM inference by utilizing otherwise idle computational resources during memory-to-chip data transfer. Current speculative decoding methods typically assume a considerable amount of avail…
RACER: Retrieval-Augmented Contextual Rapid Speculative Decoding
Autoregressive decoding in Large Language Models (LLMs) generates one token per step, causing high inference latency. Speculative decoding (SD) mitigates this through a guess-and-verify strategy, but existing training-fr…