Graph-Structured Speculative Decoding
- URL: http://arxiv.org/abs/2407.16207v1
- Date: Tue, 23 Jul 2024 06:21:24 GMT
- Title: Graph-Structured Speculative Decoding
- Authors: Zhuocheng Gong, Jiahao Liu, Ziyue Wang, Pengfei Wu, Jingang Wang, Xunliang Cai, Dongyan Zhao, Rui Yan,
- Abstract summary: Speculative decoding has emerged as a promising technique to accelerate the inference of Large Language Models.
We introduce an innovative approach utilizing a directed acyclic graph (DAG) to manage the drafted hypotheses.
We observe a remarkable speedup of 1.73$times$ to 1.96$times$, significantly surpassing standard speculative decoding.
- Score: 52.94367724136063
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Speculative decoding has emerged as a promising technique to accelerate the inference of Large Language Models (LLMs) by employing a small language model to draft a hypothesis sequence, which is then validated by the LLM. The effectiveness of this approach heavily relies on the balance between performance and efficiency of the draft model. In our research, we focus on enhancing the proportion of draft tokens that are accepted to the final output by generating multiple hypotheses instead of just one. This allows the LLM more options to choose from and select the longest sequence that meets its standards. Our analysis reveals that hypotheses produced by the draft model share many common token sequences, suggesting a potential for optimizing computation. Leveraging this observation, we introduce an innovative approach utilizing a directed acyclic graph (DAG) to manage the drafted hypotheses. This structure enables us to efficiently predict and merge recurring token sequences, vastly reducing the computational demands of the draft model. We term this approach Graph-structured Speculative Decoding (GSD). We apply GSD across a range of LLMs, including a 70-billion parameter LLaMA-2 model, and observe a remarkable speedup of 1.73$\times$ to 1.96$\times$, significantly surpassing standard speculative decoding.
Related papers
- FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling [59.8051705468084]
Speculative sampling has emerged as an important technique for accelerating the auto-regressive generation process of large language models.
We present FR-Spec, a frequency-ranked speculative sampling framework that optimize draft candidate selection through vocabulary space compression.
arXiv Detail & Related papers (2025-02-20T18:58:10Z) - Scalable Language Models with Posterior Inference of Latent Thought Vectors [52.63299874322121]
Latent-Thought Language Models (LTMs) incorporate explicit latent thought vectors that follow an explicit prior model in latent space.
LTMs possess additional scaling dimensions beyond traditional LLMs, yielding a structured design space.
LTMs significantly outperform conventional autoregressive models and discrete diffusion models in validation perplexity and zero-shot language modeling.
arXiv Detail & Related papers (2025-02-03T17:50:34Z) - Closer Look at Efficient Inference Methods: A Survey of Speculative Decoding [1.3479499607624648]
Speculative decoding addresses bottleneck by introducing a two-stage framework: drafting and verification.
A smaller, efficient model generates a preliminary draft, which is then refined by a larger, more sophisticated model.
This paper provides a comprehensive survey of speculative decoding methods, categorizing them into draft-centric and model-centric approaches.
arXiv Detail & Related papers (2024-11-20T09:46:30Z) - Boosting Lossless Speculative Decoding via Feature Sampling and Partial Alignment Distillation [8.046705062670096]
Lossless speculative decoding accelerates target large language model inference.
We propose FSPAD (Feature Sampling and Partial Alignment Distillation for Lossless Speculative Decoding) to boost speculative decoding.
Our experiments include both greedy and non-greedy decoding on the largest and smallest models from the Vicuna and LLaMA3-Instruct series.
arXiv Detail & Related papers (2024-08-28T06:28:01Z) - Adaptive Draft-Verification for Efficient Large Language Model Decoding [24.347886232342862]
Large language model (LLM) decoding involves generating a sequence of tokens based on a given context.
The typical autoregressive decoding method requires a separate forward pass through the model for each token generated.
We introduce ADED, which accelerates LLM decoding without requiring fine-tuning.
arXiv Detail & Related papers (2024-06-27T22:20:39Z) - 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) - GliDe with a CaPE: A Low-Hassle Method to Accelerate Speculative
Decoding [81.01996600734616]
We introduce GliDe and CaPE, two low-hassle modifications to vanilla speculative decoding.
GliDe is a modified draft model architecture that reuses the cached keys and values from the target LLM.
We will release our code, data, and the trained draft models.
arXiv Detail & Related papers (2024-02-03T08:44:11Z) - Amortizing intractable inference in large language models [56.92471123778389]
We use amortized Bayesian inference to sample from intractable posterior distributions.
We empirically demonstrate that this distribution-matching paradigm of LLM fine-tuning can serve as an effective alternative to maximum-likelihood training.
As an important application, we interpret chain-of-thought reasoning as a latent variable modeling problem.
arXiv Detail & Related papers (2023-10-06T16:36:08Z) - Faithful Explanations of Black-box NLP Models Using LLM-generated
Counterfactuals [67.64770842323966]
Causal explanations of predictions of NLP systems are essential to ensure safety and establish trust.
Existing methods often fall short of explaining model predictions effectively or efficiently.
We propose two approaches for counterfactual (CF) approximation.
arXiv Detail & Related papers (2023-10-01T07:31:04Z)
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.