Fast Inference from Transformers via Speculative Decoding

• URL: http://arxiv.org/abs/2211.17192v2
• Date: Thu, 18 May 2023 20:28:20 GMT
• Title: Fast Inference from Transformers via Speculative Decoding
• Authors: Yaniv Leviathan, Matan Kalman, Yossi Matias
• Abstract summary: 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.
• Score: 3.950600027250452
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• AMUSD: Asynchronous Multi-Device Speculative Decoding for LLM Acceleration [0.3626013617212667]
  We introduce AMUSD (Asynchronous Multi-device Speculative Decoding), a system that accelerates generation by decoupling the draft and verify phases. Unlike conventional speculative decoding, where only one model (draft or verify) performs token generation at a time, AMUSD enables both models to perform predictions independently on separate devices. We evaluate our approach over multiple datasets and show that AMUSD achieves an average 29% improvement over speculative decoding and up to 1.96$times$ speedup over conventional autoregressive decoding.
  arXiv  Detail & Related papers  (2024-10-22T19:15:35Z)
• Promises and Pitfalls of Generative Masked Language Modeling: Theoretical Framework and Practical Guidelines [74.42485647685272]
  We focus on Generative Masked Language Models (GMLMs) We train a model to fit conditional probabilities of the data distribution via masking, which are subsequently used as inputs to a Markov Chain to draw samples from the model. We adapt the T5 model for iteratively-refined parallel decoding, achieving 2-3x speedup in machine translation with minimal sacrifice in quality.
  arXiv  Detail & Related papers  (2024-07-22T18:00:00Z)
• Efficient Encoder-Decoder Transformer Decoding for Decomposable Tasks [53.550782959908524]
  We introduce a new configuration for encoder-decoder models that improves efficiency on structured output and decomposable tasks. Our method, prompt-in-decoder (PiD), encodes the input once and decodes the output in parallel, boosting both training and inference efficiency.
  arXiv  Detail & Related papers  (2024-03-19T19:27:23Z)
• Tandem Transformers for Inference Efficient LLMs [49.75726447408795]
  We introduce a novel architecture, Tandem transformers, to address these issues. This architecture uniquely combines a small autoregressive model and a large model operating in block mode. On the PaLM2 pretraining dataset, a tandem of PaLM2-Bison and PaLM2-Gecko demonstrates a 3.3% improvement in next-token prediction accuracy.
  arXiv  Detail & Related papers  (2024-02-13T18:24:08Z)
• Accelerating Transformer Inference for Translation via Parallel Decoding [2.89306442817912]
  Autoregressive decoding limits the efficiency of transformers for Machine Translation (MT) We present three parallel decoding algorithms and test them on different languages and models.
  arXiv  Detail & Related papers  (2023-05-17T17:57:34Z)
• Accelerating Large Language Model Decoding with Speculative Sampling [9.851546623666588]
  speculative sampling is an algorithm for accelerating transformer decoding by enabling the generation of multiple tokens from each transformer call. We benchmark speculative sampling with Chinchilla, a 70 billion parameter language model, achieving a 2-2.5x decoding speedup in a distributed setup.
  arXiv  Detail & Related papers  (2023-02-02T18:44:11Z)
• Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition [62.83832841523525]
  We propose a fast and accurate parallel transformer, termed Paraformer. It accurately predicts the number of output tokens and extract hidden variables. It can attain comparable performance to the state-of-the-art AR transformer, with more than 10x speedup.
  arXiv  Detail & Related papers  (2022-06-16T17:24:14Z)
• FastSeq: Make Sequence Generation Faster [20.920579109726024]
  We develop FastSeq framework to accelerate sequence generation without accuracy loss. benchmark results on a set of widely used and diverse models demonstrate 4-9x inference speed gain. FastSeq is easy to use with a simple one-line code change.
  arXiv  Detail & Related papers  (2021-06-08T22:25:28Z)
• Fast Interleaved Bidirectional Sequence Generation [90.58793284654692]
  We introduce a decoder that generates target words from the left-to-right and right-to-left directions simultaneously. We show that we can easily convert a standard architecture for unidirectional decoding into a bidirectional decoder. Our interleaved bidirectional decoder (IBDecoder) retains the model simplicity and training efficiency of the standard Transformer.
  arXiv  Detail & Related papers  (2020-10-27T17:38:51Z)
• Cascaded Text Generation with Markov Transformers [122.76100449018061]
  Two dominant approaches to neural text generation are fully autoregressive models, using serial beam search decoding, and non-autoregressive models, using parallel decoding with no output dependencies. This work proposes an autoregressive model with sub-linear parallel time generation. Noting that conditional random fields with bounded context can be decoded in parallel, we propose an efficient cascaded decoding approach for generating high-quality output. This approach requires only a small modification from standard autoregressive training, while showing competitive accuracy/speed tradeoff compared to existing methods on five machine translation datasets.
  arXiv  Detail & Related papers  (2020-06-01T17:52:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.