Token-Driven GammaTune: Adaptive Calibration for Enhanced Speculative Decoding

• URL: http://arxiv.org/abs/2504.00030v2
• Date: Thu, 03 Apr 2025 12:31:40 GMT
• Title: Token-Driven GammaTune: Adaptive Calibration for Enhanced Speculative Decoding
• Authors: Aayush Gautam, Susav Shrestha, Narasimha Reddy,
• Abstract summary: Speculative decoding accelerates large language model inference.<n>We introduce textitGammaTune and textitGammaTune+, training-free adaptive algorithms that dynamically adjust speculation length based on token acceptance rates.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Speculative decoding accelerates large language model (LLM) inference by using a smaller draft model to propose tokens, which are then verified by a larger target model. However, selecting an optimal speculation length is critical for maximizing speedup while minimizing wasted computation. We introduce \textit{GammaTune} and \textit{GammaTune+}, training-free adaptive algorithms that dynamically adjust speculation length based on token acceptance rates using a heuristic-based switching mechanism. Evaluated on SpecBench across multiple tasks and model pairs, our method outperforms other heuristic-based approaches and fixed-length speculative decoding, achieving an average speedup of 15\% ($\pm$5\%) with \textit{GammaTune} and 16\% ($\pm$3\%) with \textit{GammaTune+}, while reducing performance variance. This makes \textit{GammaTune} a robust and efficient solution for real-world deployment.

Related papers

• $\ exttt{SPECS}$: Faster Test-Time Scaling through Speculative Drafts [55.231201692232894]
  $textttSPECS$ is a latency-aware test-time scaling method inspired by speculative decoding.<n>Our results show that $textttSPECS$matches or surpasses beam search accuracy while reducing latency by up to $sim$19.1%.
  arXiv  Detail & Related papers  (2025-06-15T05:50:05Z)
• Automatic mixed precision for optimizing gained time with constrained loss mean-squared-error based on model partition to sequential sub-graphs [0.8999666725996975]
  Mixed Precision (MP) mitigates the tradeoff by varying numerical precision across network layers.<n>This study focuses on automatically selecting an optimal MP configuration within Post-Training Quantization (PTQ) for inference.
  arXiv  Detail & Related papers  (2025-05-19T12:51:02Z)
• AutoJudge: Judge Decoding Without Manual Annotation [10.411318392966358]
  AutoJudge is a framework that accelerates large language model (LLM) inference with task-specific lossy speculative decoding. We use a semi-greedy search algorithm to test which of the mismatches between target and draft model should be corrected. We then train a lightweight classifier based on existing LLM embeddings to predict, at inference time, which mismatching tokens can be safely accepted.
  arXiv  Detail & Related papers  (2025-04-28T17:59:28Z)
• GRIFFIN: Effective Token Alignment for Faster Speculative Decoding [52.905060461479856]
  GRIFFIN is a framework that incorporates a token-alignable training strategy and a token-alignable draft model.<n>Experiments on LLaMA-series and Vicuna models demonstrate that GRIFFIN achieves an average acceptance length improvement of over 7% and a speedup ratio exceeding 8%.
  arXiv  Detail & Related papers  (2025-02-16T07:06:00Z)
• Graph-Structured Speculative Decoding [52.94367724136063]
  Speculative decoding has emerged as a promising technique to accelerate the inference of Large Language Models. We introduce an innovative approach utilizing a directed acyclic graph (DAG) to manage the drafted hypotheses. We observe a remarkable speedup of 1.73$times$ to 1.96$times$, significantly surpassing standard speculative decoding.
  arXiv  Detail & Related papers  (2024-07-23T06:21:24Z)
• Hardware-Aware Parallel Prompt Decoding for Memory-Efficient Acceleration of LLM Inference [19.167604927651073]
  Auto-regressive decoding of Large Language Models (LLMs) results in significant overheads in their hardware performance. We propose a novel parallel prompt decoding that requires only $0.0002$% trainable parameters, enabling efficient training on a single A100-40GB GPU in just 16 hours. Our approach demonstrates up to 2.49$times$ speedup and maintains a minimal memory overhead of just $0.0004$%.
  arXiv  Detail & Related papers  (2024-05-28T22:19:30Z)
• EMS-SD: Efficient Multi-sample Speculative Decoding for Accelerating Large Language Models [40.651650382105636]
  Vanilla method adds padding tokens in order to ensure that the number of new tokens remains consistent across samples. We propose a novel method that can resolve the issue of inconsistent tokens accepted by different samples without necessitating an increase in memory or computing overhead. Our proposed method can handle the situation where the prediction tokens of different samples are inconsistent without the need to add padding tokens.
  arXiv  Detail & Related papers  (2024-05-13T08:24:21Z)
• Fine-Tuning Adaptive Stochastic Optimizers: Determining the Optimal Hyperparameter $ε$ via Gradient Magnitude Histogram Analysis [0.7366405857677226]
  We introduce a new framework based on the empirical probability density function of the loss's magnitude, termed the "gradient magnitude histogram" We propose a novel algorithm using gradient magnitude histograms to automatically estimate a refined and accurate search space for the optimal safeguard.
  arXiv  Detail & Related papers  (2023-11-20T04:34:19Z)
• SpecTr: Fast Speculative Decoding via Optimal Transport [30.18181671899423]
  We develop a new autoregressive sampling algorithm called $textitSpecTr$, which provides speedup in decoding while ensuring that there is no quality degradation in the decoded output. We experimentally demonstrate that for state-of-the-art large language models, the proposed approach achieves a wall clock speedup of 2.13X, a further 1.37X speedup over speculative decoding on standard benchmarks.
  arXiv  Detail & Related papers  (2023-10-23T17:47:34Z)
• Distributed Extra-gradient with Optimal Complexity and Communication Guarantees [60.571030754252824]
  We consider monotone variational inequality (VI) problems in multi-GPU settings where multiple processors/workers/clients have access to local dual vectors. Extra-gradient, which is a de facto algorithm for monotone VI problems, has not been designed to be communication-efficient. We propose a quantized generalized extra-gradient (Q-GenX), which is an unbiased and adaptive compression method tailored to solve VIs.
  arXiv  Detail & Related papers  (2023-08-17T21:15:04Z)
• AMOM: Adaptive Masking over Masking for Conditional Masked Language Model [81.55294354206923]
  A conditional masked language model (CMLM) is one of the most versatile frameworks. We introduce a simple yet effective adaptive masking over masking strategy to enhance the refinement capability of the decoder. Our proposed model yields state-of-the-art performance on neural machine translation.
  arXiv  Detail & Related papers  (2023-03-13T20:34:56Z)
• Decoder Tuning: Efficient Language Understanding as Decoding [84.68266271483022]
  We present Decoder Tuning (DecT), which in contrast optimize task-specific decoder networks on the output side. By gradient-based optimization, DecT can be trained within several seconds and requires only one P query per sample. We conduct extensive natural language understanding experiments and show that DecT significantly outperforms state-of-the-art algorithms with a $200times$ speed-up.
  arXiv  Detail & Related papers  (2022-12-16T11:15:39Z)
• BBTv2: Pure Black-Box Optimization Can Be Comparable to Gradient Descent for Few-Shot Learning [83.26610968655815]
  Black-Box Tuning is a derivative-free approach to optimize continuous prompt tokens prepended to the input of language models. We present BBTv2, a pure black-box optimization approach that can drive language models to achieve comparable results to gradient-based optimization.
  arXiv  Detail & Related papers  (2022-05-23T11:10:19Z)
• Joint inference and input optimization in equilibrium networks [68.63726855991052]
  deep equilibrium model is a class of models that foregoes traditional network depth and instead computes the output of a network by finding the fixed point of a single nonlinear layer. We show that there is a natural synergy between these two settings. We demonstrate this strategy on various tasks such as training generative models while optimizing over latent codes, training models for inverse problems like denoising and inpainting, adversarial training and gradient based meta-learning.
  arXiv  Detail & Related papers  (2021-11-25T19:59:33Z)
• Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints [29.227720674726413]
  We propose a fast minimum-norm (FMN) attack that works with different $ell_p$-norm perturbation models. Experiments show that FMN significantly outperforms existing attacks in terms of convergence speed and time.
  arXiv  Detail & Related papers  (2021-02-25T12:56:26Z)

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.