EMS-SD: Efficient Multi-sample Speculative Decoding for Accelerating Large Language Models

TL;DR

This paper introduces EMS-SD, a novel multi-sample speculative decoding method that improves inference speed for large language models by resolving token acceptance inconsistencies without extra overhead.

Contribution

The paper presents a new approach to multi-sample speculative decoding that eliminates the need for padding tokens, reducing computational and memory overhead.

Findings

Significant speedup in LLM inference demonstrated

Reduced computational overhead compared to vanilla methods

Effective handling of token acceptance inconsistencies

Abstract

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 has been overlooked due to varying numbers of accepted tokens within a batch in the verification phase. Vanilla method adds padding tokens in order to ensure that the number of new tokens remains consistent across samples. However, this increases the computational and memory access overhead, thereby reducing the speedup ratio. We propose a novel method that can resolve the issue of inconsistent tokens accepted by different samples without necessitating an increase in memory or computing overhead. Furthermore, our proposed method can handle the situation where the prediction tokens of different samples are inconsistent without the need to add padding tokens. Sufficient experiments demonstrate the efficacy of our method. Our code is available at https://github.com/niyunsheng/EMS-SD.