TETRIS: Optimal Draft Token Selection for Batch Speculative Decoding

TL;DR

TETRIS is a new method that improves batch speculative decoding in large language models by actively selecting the most promising draft tokens for multiple requests, increasing throughput and resource efficiency.

Contribution

TETRIS introduces an active draft token selection strategy that optimizes throughput in multi-request batch decoding, outperforming existing methods.

Findings

Higher acceptance rate than baseline methods

More effective utilization of inference capacity

Consistently better performance in empirical tests

Abstract

We propose TETRIS, a novel method that optimizes the total throughput of batch speculative decoding in multi-request settings. Unlike existing methods that optimize for a single request or a group of requests as a whole, TETRIS actively selects the most promising draft tokens (for every request in a batch) to be accepted when verified in parallel, resulting in fewer rejected tokens and hence less wasted computing resources. Such an effective resource utilization to achieve fast inference in large language models (LLMs) is especially important to service providers with limited inference capacity. Compared to baseline speculative decoding, TETRIS yields a consistently higher acceptance rate and more effective utilization of the limited inference capacity. We show theoretically and empirically that TETRIS outperforms baseline speculative decoding and existing methods that dynamically select draft tokens, leading to a more efficient batch inference in LLMs.