Accelerating LLM Inference with Staged Speculative Decoding

Benjamin Frederick Spector, Christopher Re

Keywords: foundation model, large language model, inference, efficiency, edge, artificial intelligence, open source

TL;DR: Using stages of small models to anticipate a LLM's predictions, you can batch queries to it and reduce inference latencies by 3x.

Abstract: Recent advances with large language models (LLM) illustrate their diverse capabilities. We propose a novel algorithm, staged speculative decoding, to accelerate LLM inference in small-batch, on-device scenarios. We address the low arithmetic intensity of small-batch inference by improving upon previous work in speculative decoding. First, we restructure the speculative batch as a tree, which reduces generation costs and increases the expected tokens per batch. Second, we add a second stage of speculative decoding. Taken together, we reduce single-batch decoding latency by 3.16x with a 762M parameter GPT-2-L model while perfectly preserving output quality.

Submission Number: 47