Speculative Decoding for Multi-Sample Inference
We propose a novel speculative decoding method tailored for multi-sample reasoning scenarios, such as self-consistency and Best-of-N sampling. Our method exploits the intrinsic consensus of parallel generation paths to synthesize high-quality draft tokens without requiring auxiliary models or external databases. By dynamically analyzing structural patterns across parallel reasoning paths through a probabilistic aggregation mechanism, it identifies consensus token sequences that align with the decoding distribution. Evaluations on mathematical reasoning benchmarks demonstrate a substantial improvement in draft acceptance rates over baselines, while reducing the latency in draft token construction. This work establishes a paradigm shift for efficient multi-sample inference, enabling seamless integration of speculative decoding with sampling-based reasoning techniques.
Code (0)
등록된 구현이 없습니다.
Tasks
Mathematical ReasoningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
A Theoretical Perspective for Speculative Decoding Algorithm
Transformer-based autoregressive sampling has been the major bottleneck for slowing down large language model inferences. One effective way to accelerate inference is \emph{Speculative Decoding}, which employs a small mo…
Language ModelingLanguage ModellingLarge Language ModelMMSpec: Benchmarking Speculative Decoding for Vision-Language Models
Vision-language models (VLMs) achieve strong performance on multimodal tasks but suffer from high inference latency due to large model sizes and long multimodal contexts. Speculative decoding has recently emerged as an e…
Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding
To mitigate the high inference latency stemming from autoregressive decoding in Large Language Models (LLMs), Speculative Decoding has emerged as a novel decoding paradigm for LLM inference. In each decoding step, this m…
Language ModelingLanguage ModellingLarge Language ModelVariational Speculative Decoding: Rethinking Draft Training from Token Likelihood to Sequence Acceptance
Speculative decoding accelerates inference for (M)LLMs, yet a training-decoding discrepancy persists: while existing methods optimize single greedy trajectories, decoding involves verifying and ranking multiple sampled d…
EMS-SD: Efficient Multi-sample Speculative Decoding for Accelerating Large Language Models
Speculative decoding emerges as a pivotal technique for enhancing the inference speed of Large Language Models (LLMs). Despite recent research aiming to improve prediction efficiency, multi-sample speculative decoding ha…