Falcon: Faster and Parallel Inference of Large Language Models through Enhanced Semi-Autoregressive Drafting and Custom-Designed Decoding Tree

• URL: http://arxiv.org/abs/2412.12639v2
• Date: Thu, 26 Dec 2024 06:20:21 GMT
• Title: Falcon: Faster and Parallel Inference of Large Language Models through Enhanced Semi-Autoregressive Drafting and Custom-Designed Decoding Tree
• Authors: Xiangxiang Gao, Weisheng Xie, Yiwei Xiang, Feng Ji,
• Abstract summary: Falcon is an innovative speculative decoding framework fashioned to augment both the drafter's parallelism and output quality. Falcon incorporates the Coupled Sequential Glancing Distillation technique, which fortifies inter-token dependencies within the same block, leading to increased speculation accuracy.
• Score: 7.438117410146904
• License:
• Abstract: Striking an optimal balance between minimal drafting latency and high speculation accuracy to enhance the inference speed of Large Language Models remains a significant challenge in speculative decoding. In this paper, we introduce Falcon, an innovative semi-autoregressive speculative decoding framework fashioned to augment both the drafter's parallelism and output quality. Falcon incorporates the Coupled Sequential Glancing Distillation technique, which fortifies inter-token dependencies within the same block, leading to increased speculation accuracy. We offer a comprehensive theoretical analysis to illuminate the underlying mechanisms. Additionally, we introduce a Custom-Designed Decoding Tree, which permits the drafter to generate multiple tokens in a single forward pass and accommodates multiple forward passes as needed, thereby boosting the number of drafted tokens and significantly improving the overall acceptance rate. Comprehensive evaluations on benchmark datasets such as MT-Bench, HumanEval, and GSM8K demonstrate Falcon's superior acceleration capabilities. The framework achieves a lossless speedup ratio ranging from 2.91x to 3.51x when tested on the Vicuna and LLaMA2-Chat model series. These results outstrip existing speculative decoding methods for LLMs, including Eagle, Medusa, Lookahead, SPS, and PLD, while maintaining a compact drafter architecture equivalent to merely two Transformer layers.

Related papers

• Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE [15.003006630308517]
  Speculative decoding (SD) accelerates large language model inference by using a smaller draft model to predict multiple tokens. We propose Jakiro, leveraging Mixture of Experts (MoE), where independent experts generate diverse predictions. Our method significantly boosts prediction accuracy and achieves higher inference speedups.
  arXiv  Detail & Related papers  (2025-02-10T09:24:06Z)
• ParallelSpec: Parallel Drafter for Efficient Speculative Decoding [62.68430939686566]
  We present ParallelSpec, an alternative to auto-regressive drafting strategies in state-of-the-art speculative decoding approaches. In contrast to auto-regressive drafting in the speculative stage, we train a parallel drafter to serve as an efficient speculative model.
  arXiv  Detail & Related papers  (2024-10-08T01:05:08Z)
• Parallel Decoding via Hidden Transfer for Lossless Large Language Model Acceleration [54.897493351694195]
  We propose a novel parallel decoding approach, namely textithidden transfer, which decodes multiple successive tokens simultaneously in a single forward pass. In terms of acceleration metrics, we outperform all the single-model acceleration techniques, including Medusa and Self-Speculative decoding.
  arXiv  Detail & Related papers  (2024-04-18T09:17:06Z)
• SDSAT: Accelerating LLM Inference through Speculative Decoding with Semantic Adaptive Tokens [4.5888031410244885]
  We propose an acceleration scheme for large language models (LLMs) through Speculative Decoding with Semantic Adaptive Tokens (SDSAT) The primary objective of this design is to enhance the LLM model's ability to generate draft tokens more accurately without compromising its accuracy. Experiments conducted on the CodeLlama-13B and 7B models have yielded speed increases of over 3.5X and 3.0X, respectively.
  arXiv  Detail & Related papers  (2024-03-27T14:54:27Z)
• Chimera: A Lossless Decoding Method for Accelerating Large Language Models Inference by Fusing all Tokens [15.566726645722657]
  We propose a novel framework specifically designed for speculative sampling. Within this framework, we introduce a lightweight draft model that effectively utilizes previously generated tokens to predict subsequent words. We demonstrate impressive results, achieving an average latency speedup ratio of 2.7x compared to the vanilla auto-regressive decoding approach.
  arXiv  Detail & Related papers  (2024-02-24T08:10:39Z)
• Generation Meets Verification: Accelerating Large Language Model Inference with Smart Parallel Auto-Correct Decoding [11.832919020149891]
  This research aims to accelerate the inference speed of large language models (LLMs) with billions of parameters. We propose textbfSmart textbfParallel textbfAuto-textbfCorrect dtextbfEcoding (SPACE)
  arXiv  Detail & Related papers  (2024-02-19T03:39:10Z)
• Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding [43.659680579686544]
  We propose a Fast and Robust Early-Exiting framework, which incorporates a shallow-deep module and a synchronized parallel decoding. Our framework enables faster inference by synchronizing the decoding process of the current token with previously stacked early-exited tokens. As parallel decoding allows us to observe predictions from both shallow and deep models, we present a novel adaptive threshold estimator.
  arXiv  Detail & Related papers  (2023-10-09T05:53:05Z)
• 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)
• Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation [80.2267931231335]
  We propose Speculative Decoding (SpecDec) to study exploiting the idea of speculative execution to accelerate autoregressive (AR) decoding. SpecDec has two innovations: Spec-Drafter -- an independent model specially optimized for efficient drafting, and Spec-Verification -- a reliable method for verifying the drafted tokens efficiently.
  arXiv  Detail & Related papers  (2022-03-30T17:27:09Z)
• Non-autoregressive End-to-end Speech Translation with Parallel Autoregressive Rescoring [83.32560748324667]
  This article describes an efficient end-to-end speech translation (E2E-ST) framework based on non-autoregressive (NAR) models. We propose a unified NAR E2E-ST framework called Orthros, which has an NAR decoder and an auxiliary shallow AR decoder on top of the shared encoder.
  arXiv  Detail & Related papers  (2021-09-09T16:50:16Z)
• FastLR: Non-Autoregressive Lipreading Model with Integrate-and-Fire [74.04394069262108]
  We propose FastLR, a non-autoregressive (NAR) lipreading model which generates all target tokens simultaneously. FastLR achieves the speedup up to 10.97$times$ compared with state-of-the-art lipreading model.
  arXiv  Detail & Related papers  (2020-08-06T08:28:56Z)

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.