Parallel Decoding via Hidden Transfer for Lossless Large Language Model Acceleration

• URL: http://arxiv.org/abs/2404.12022v1
• Date: Thu, 18 Apr 2024 09:17:06 GMT
• Title: Parallel Decoding via Hidden Transfer for Lossless Large Language Model Acceleration
• Authors: Pengfei Wu, Jiahao Liu, Zhuocheng Gong, Qifan Wang, Jinpeng Li, Jingang Wang, Xunliang Cai, Dongyan Zhao,
• Abstract summary: 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.
• Score: 54.897493351694195
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) have recently shown remarkable performance across a wide range of tasks. However, the substantial number of parameters in LLMs contributes to significant latency during model inference. This is particularly evident when utilizing autoregressive decoding methods, which generate one token in a single forward process, thereby not fully capitalizing on the parallel computing capabilities of GPUs. In this paper, we propose a novel parallel decoding approach, namely \textit{hidden transfer}, which decodes multiple successive tokens simultaneously in a single forward pass. The idea is to transfer the intermediate hidden states of the previous context to the \textit{pseudo} hidden states of the future tokens to be generated, and then the pseudo hidden states will pass the following transformer layers thereby assimilating more semantic information and achieving superior predictive accuracy of the future tokens. Besides, we use the novel tree attention mechanism to simultaneously generate and verify multiple candidates of output sequences, which ensure the lossless generation and further improves the generation efficiency of our method. Experiments demonstrate the effectiveness of our method. We conduct a lot of analytic experiments to prove our motivation. In terms of acceleration metrics, we outperform all the single-model acceleration techniques, including Medusa and Self-Speculative decoding.

Related papers

• FIRP: Faster LLM inference via future intermediate representation prediction [54.897493351694195]
  FIRP generates multiple tokens instead of one at each decoding step. We conduct extensive experiments, showing a speedup ratio of 1.9x-3x in several models and datasets.
  arXiv  Detail & Related papers  (2024-10-27T15:53:49Z)
• 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)
• Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token Recycling [53.58854856174773]
  Speculative decoding is an approach to accelerate inference through a guess-and-verify paradigm. Token Recycling stores candidate tokens in an adjacency matrix and employs a breadth-first search algorithm. It significantly outperforms existing train-free methods by 30% and even a training method by 25%.
  arXiv  Detail & Related papers  (2024-08-16T12:20:56Z)
• 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)
• Deciphering Movement: Unified Trajectory Generation Model for Multi-Agent [53.637837706712794]
  We propose a Unified Trajectory Generation model, UniTraj, that processes arbitrary trajectories as masked inputs. Specifically, we introduce a Ghost Spatial Masking (GSM) module embedded within a Transformer encoder for spatial feature extraction. We benchmark three practical sports game datasets, Basketball-U, Football-U, and Soccer-U, for evaluation.
  arXiv  Detail & Related papers  (2024-05-27T22:15:23Z)
• 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)
• SPEED: Speculative Pipelined Execution for Efficient Decoding [35.45955948053644]
  We propose SPEED, which improves inference efficiency by speculatively executing multiple future tokens in parallel with the current token. For Transformer decoders that employ parameter sharing, the memory operations for the tokens executing in parallel can be amortized. We demonstrate the efficiency of our method in terms of latency reduction relative to model accuracy and demonstrate how speculation allows for training deeper decoders with parameter sharing with minimal runtime overhead.
  arXiv  Detail & Related papers  (2023-10-18T16:07:01Z)
• Non-Autoregressive Machine Translation with Disentangled Context Transformer [70.95181466892795]
  State-of-the-art neural machine translation models generate a translation from left to right and every step is conditioned on the previously generated tokens. We propose an attention-masking based model, called Disentangled Context (DisCo) transformer, that simultaneously generates all tokens given different contexts. Our model achieves competitive, if not better, performance compared to the state of the art in non-autoregressive machine translation while significantly reducing decoding time on average.
  arXiv  Detail & Related papers  (2020-01-15T05:32:18Z)

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.