Sequoia: Scalable and Robust Speculative Decoding

Zhuoming Chen, Avner May, Ruslan Svirschevski, Yu-Hsun Huang, Max Ryabinin, Zhihao Jia, Beidi Chen

Keywords: LLM inference; Speculative Decoding

TL;DR: Accelerate LLM inference with a scalable and robust tree based speculative decoding algorithm

Abstract: As the usage of large language models (LLMs) grows, it becomes increasingly important to serve them quickly and efficiently. While speculative decoding has recently emerged as a promising direction for accelerating LLM serving, existing methods are limited in their ability to scale to larger speculation budgets and adapt to different hyperparameters. This paper introduces Sequoia, a scalable and robust algorithm for speculative decoding. To improve scalability, Sequoia introduces a dynamic programming algorithm to find an optimal tree structure for the speculated tokens. To achieve robust speculative decoding, Sequoia uses a novel sampling and verification method that outperforms prior work across different decoding temperatures. Sequoia improves the decoding speed of Llama2-7B, Llama2-13B, and Vicuna-33B on an A100 GPU by up to $4.04\times$, $3.73\times$, and $2.27 \times$. To serve Llama3-70B-Instruct on a single L40 GPU through offloading, Sequoia reduces the per-token decoding latency to 0.60 s/token, $9.5\times$ faster than DeepSpeed-Zero-Inference.

Primary Area: Natural language processing

Submission Number: 2560