arXiv:2211.17192cs.LG
Fast Inference from Transformers via Speculative Decoding
Abstract
Inference from large autoregressive models like Transformers is slow - decoding K tokens takes K serial runs of the model. In this work we introduce speculative decoding - an algorithm to sample from autoregressive models faster without any changes to the outputs, by computing several tokens in parallel. At the heart of our approach lie the observations that (1) hard language-modeling tasks often include easier subtasks that can be approximated well by more efficient models, and (2) using speculative execution and a novel sampling method, we can make exact decoding from the large models faster, by running them in parallel on the outputs of the approximation models, potentially generating several tokens concurrently, and without changing the distribution. Our method can accelerate existing off-the-shelf models without retraining or architecture changes. We demonstrate it on T5-XXL and show a 2X-3X acceleration compared to the standard T5X implementation, with identical outputs.
Title is bad, it's the first line of the abstract instead of the paper title. Speculative decoding for LLM inference was published in 2022: https://arxiv.org/abs/2211.17192 This paper seems to be an improvement to speculative decoding but I haven't read it yet.
articlepanView on HNParent context
Is this newer/better than the speculative decoding from 2022? https://arxiv.org/abs/2211.17192
xnxView on HNParent context
>publish these incredible papers explaining how they achieved their gains - something the American labs no longer do unfortunately. Google is still releasing a lot of llm architecture research. They introduced speculative decoding of LLMs in 2022[1], then released the code to…
sigmarView on HNParent context