Learning to Keep a Promise: Scaling Language Model Decoding Parallelism with Learned Asynchronous Decoding

• URL: http://arxiv.org/abs/2502.11517v2
• Date: Fri, 21 Feb 2025 06:14:19 GMT
• Title: Learning to Keep a Promise: Scaling Language Model Decoding Parallelism with Learned Asynchronous Decoding
• Authors: Tian Jin, Ellie Y. Cheng, Zack Ankner, Nikunj Saunshi, Blake M. Elias, Amir Yazdanbakhsh, Jonathan Ragan-Kelley, Suvinay Subramanian, Michael Carbin,
• Abstract summary: PASTA is a learning-based system that teaches large language models to identify semantic independence and express parallel decoding opportunities in their own responses.<n> PASTA-Lang is an annotation language that enables LLMs to express semantic independence in their own responses.<n>Our results demonstrate geometric mean speedups ranging from 1.21x to 1.93x with corresponding quality changes of +2.2% to -7.1%, measured by length-controlled win rates against sequential decoding baseline.
• Score: 26.571743941748238
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Decoding with autoregressive large language models (LLMs) traditionally occurs sequentially, generating one token after another. An emerging line of work explored parallel decoding by identifying and simultaneously generating semantically independent chunks of LLM responses. However, these techniques rely on hand-crafted heuristics tied to syntactic structures like lists and paragraphs, making them rigid and imprecise. We present PASTA, a learning-based system that teaches LLMs to identify semantic independence and express parallel decoding opportunities in their own responses. At its core are PASTA-LANG and its interpreter: PASTA-LANG is an annotation language that enables LLMs to express semantic independence in their own responses; the language interpreter acts on these annotations to orchestrate parallel decoding on-the-fly at inference time. Through a two-stage finetuning process, we train LLMs to generate PASTA-LANG annotations that optimize both response quality and decoding speed. Evaluation on AlpacaEval, an instruction following benchmark, shows that our approach Pareto-dominates existing methods in terms of decoding speed and response quality; our results demonstrate geometric mean speedups ranging from 1.21x to 1.93x with corresponding quality changes of +2.2% to -7.1%, measured by length-controlled win rates against sequential decoding baseline.

Related papers

• CAAD: Context-Aware Adaptive Decoding for Truthful Text Generation [31.469511576774252]
  We propose a context-aware adaptive decoding method for large language models.<n>Our approach achieves a 2.8 percent average improvement on TruthfulQA.<n>Our model-agnostic, scalable, and efficient method requires only a single generation pass.
  arXiv  Detail & Related papers  (2025-08-04T08:28:25Z)
• DecoRTL: A Run-time Decoding Framework for RTL Code Generation with LLMs [0.0]
  We show that large language models (LLMs) exhibit low confidence in regions of structural ambiguity or semantic complexity.<n>We introduce DecoRTL, a novel run-time decoding strategy, that is both syntax-aware and contrastive for RTL code generation.<n>Our approach operates entirely at inference time without requiring any additional model fine-tuning.
  arXiv  Detail & Related papers  (2025-07-03T01:17:44Z)
• PARALLELPROMPT: Extracting Parallelism from Large Language Model Queries [16.40921376558516]
  We introduce PARALLELPROMPT, the first benchmark for measuring intra-query parallelism in natural user prompts.<n>Our dataset comprises over 37,000 real-world prompts from public LLM chat logs.<n>We provide an execution suite that benchmarks serial vs. parallel strategies, measuring latency, structural adherence, and semantic fidelity.
  arXiv  Detail & Related papers  (2025-06-23T15:05:54Z)
• Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding [51.711605076319216]
  Diffusion-based large language models (Diffusion LLMs) have shown promise for non-autoregressive text generation with parallel decoding capabilities.<n>We introduce a novel block-wise approximate KV Cache mechanism tailored for bidirectional diffusion models, enabling cache reuse with negligible performance drop.<n>We propose a confidence-aware parallel decoding strategy that selectively decodes tokens exceeding a confidence threshold, mitigating dependency violations and maintaining generation quality.
  arXiv  Detail & Related papers  (2025-05-28T17:39:15Z)
• LatentQA: Teaching LLMs to Decode Activations Into Natural Language [72.87064562349742]
  We introduce LatentQA, the task of answering open-ended questions about model activations in natural language.<n>We propose Latent Interpretation Tuning (LIT), which finetunes a decoder LLM on a dataset of activations and associated question-answer pairs.<n>Our decoder also specifies a differentiable loss that we use to control models, such as debiasing models on stereotyped sentences and controlling the sentiment of generations.
  arXiv  Detail & Related papers  (2024-12-11T18:59:33Z)
• CLLMs: Consistency Large Language Models [18.17892007267927]
  Jacobi decoding achieves little speedup compared to traditional autoregressive (AR) decoding. We develop a new approach aimed at realizing fast convergence from any state to the fixed point on a Jacobi trajectory.
  arXiv  Detail & Related papers  (2024-02-28T20:17:04Z)
• 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)
• Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding [46.485363806259265]
  Speculative Decoding has emerged as a novel decoding paradigm for Large Language Models (LLMs) inference. In each decoding step, this method first drafts several future tokens efficiently and then verifies them in parallel. This paper presents a comprehensive overview and analysis of this promising decoding paradigm.
  arXiv  Detail & Related papers  (2024-01-15T17:26:50Z)
• Speech Translation with Large Language Models: An Industrial Practice [64.5419534101104]
  We introduce LLM-ST, a novel and effective speech translation model constructed upon a pre-trained large language model (LLM) By integrating the large language model (LLM) with a speech encoder and employing multi-task instruction tuning, LLM-ST can produce accurate timestamped transcriptions and translations. Through rigorous experimentation on English and Chinese datasets, we showcase the exceptional performance of LLM-ST.
  arXiv  Detail & Related papers  (2023-12-21T05:32:49Z)
• Fast Chain-of-Thought: A Glance of Future from Parallel Decoding Leads to Answers Faster [61.83949316226113]
  FastCoT is a model-agnostic framework based on parallel decoding. We show that FastCoT saves inference time by nearly 20% with only a negligible performance drop compared to the regular approach.
  arXiv  Detail & Related papers  (2023-11-14T15:56:18Z)
• Harnessing the Zero-Shot Power of Instruction-Tuned Large Language Model in End-to-End Speech Recognition [23.172469312225694]
  We propose to utilize an instruction-tuned large language model (LLM) for guiding the text generation process in automatic speech recognition (ASR)<n>The proposed model is built on the joint CTC and attention architecture, with the LLM serving as a front-end feature extractor for the decoder.<n> Experimental results show that the proposed LLM-guided model achieves a relative gain of approximately 13% in word error rates across major benchmarks.
  arXiv  Detail & Related papers  (2023-09-19T11:10:50Z)
• Instruction Position Matters in Sequence Generation with Large Language Models [67.87516654892343]
  Large language models (LLMs) are capable of performing conditional sequence generation tasks, such as translation or summarization. We propose enhancing the instruction-following capability of LLMs by shifting the position of task instructions after the input sentences.
  arXiv  Detail & Related papers  (2023-08-23T12:36:57Z)
• Inference with Reference: Lossless Acceleration of Large Language Models [97.04200102556551]
  LLMA is an accelerator to speed up Large Language Model (LLM) inference with references. It is motivated by the observation that there are abundant identical text spans between the decoding result by an LLM and the reference that is available in many real world scenarios.
  arXiv  Detail & Related papers  (2023-04-10T09:55:14Z)
• Improving Mandarin End-to-End Speech Recognition with Word N-gram Language Model [57.92200214957124]
  External language models (LMs) are used to improve the recognition performance of end-to-end (E2E) automatic speech recognition (ASR) systems. We propose a novel decoding algorithm where a word-level lattice is constructed on-the-fly to consider all possible word sequences. Our method consistently outperforms subword-level LMs, including N-gram LM and neural network LM.
  arXiv  Detail & Related papers  (2022-01-06T10:04:56Z)

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.