English
Related papers

Related papers: SAGE: Accelerating Vision-Language Models via Entr…

200 papers

Inference with modern Large Language Models (LLMs) is expensive and time-consuming, and speculative sampling has proven to be an effective solution. Most speculative sampling methods such as EAGLE use a static draft tree, implicitly…

Computation and Language · Computer Science 2024-07-02 Yuhui Li , Fangyun Wei , Chao Zhang , Hongyang Zhang

Speculative decoding (SD) has emerged as an effective technique to accelerate large language model (LLM) inference without compromising output quality. However, the achievable speedup largely depends on the effectiveness of the drafting…

Computation and Language · Computer Science 2025-11-04 Min Fang , Zhihui Fu , Qibin Zhao , Jun Wang

Vision-Language-Action (VLA) models have made substantial progress by leveraging the robust capabilities of Visual Language Models (VLMs). However, VLMs' significant parameter size and autoregressive (AR) decoding nature impose considerable…

Machine Learning · Computer Science 2025-09-23 Songsheng Wang , Rucheng Yu , Zhihang Yuan , Chao Yu , Feng Gao , Yu Wang , Derek F. Wong

Tree-based speculative decoding accelerates autoregressive generation by verifying a branching tree of draft tokens in a single target-model forward pass. However, existing methods prioritize maximizing token-level likelihood or the number…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-04-14 Lifu Wang , Pan Zhou

Large language models are unable to continuously adapt and learn from new data during reasoning at inference time. To address this limitation, we propose that complex reasoning tasks be decomposed into atomic subtasks and introduce SAGE, a…

Computation and Language · Computer Science 2025-09-09 Jiacheng Wei , Faguo Wu , Xiao Zhang

Speculative decoding is a promising approach for accelerating large language models. The primary idea is to use a lightweight draft model to speculate the output of the target model for multiple subsequent timesteps, and then verify them in…

Computation and Language · Computer Science 2025-11-06 Yepeng Weng , Qiao Hu , Xujie Chen , Li Liu , Dianwen Mei , Huishi Qiu , Jiang Tian , Zhongchao Shi

Speculative decoding is widely adopted to reduce latency in large language model (LLM) inference by leveraging smaller draft models capable of handling diverse user tasks. However, emerging AI applications, such as LLM-based agents, present…

Computation and Language · Computer Science 2025-10-09 Gabriele Oliaro , Zhihao Jia , Daniel Campos , Aurick Qiao

Vision-Language Models (VLMs) have made striking progress, yet their spatial reasoning remains fragile: models that answer an original input correctly can still fail under paired transformations with predictable answer mappings, revealing a…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Junming Liu , Yuqi Li , Yifei Sun , Maonan Wang , Piotr Koniusz , Yirong Chen , Ding Wang

Speculative decoding has emerged as an effective approach for accelerating autoregressive inference by parallelizing token generation through a draft-then-verify paradigm. However, existing methods rely on static drafting lengths and rigid…

Computation and Language · Computer Science 2026-05-29 Jaydip Sen , Subhasis Dasgupta , Hetvi Waghela

Speculative decoding (SD) has emerged as a powerful method for accelerating autoregressive generation in large language models (LLMs), yet its integration into vision-language models (VLMs) remains underexplored. We introduce DREAM, a novel…

Computation and Language · Computer Science 2025-10-24 Yunhai Hu , Tianhua Xia , Zining Liu , Rahul Raman , Xingyu Liu , Bo Bao , Eric Sather , Vithursan Thangarasa , Sai Qian Zhang

Speculative decoding accelerates Large Language Model inference via a draft-then-verify paradigm, yet the output projection layer becomes a bottleneck as vocabulary sizes scale. While existing static pruning methods effectively reduce this…

Computation and Language · Computer Science 2026-05-29 Shuyu Zhang , Lingfeng Pan , Qicheng Wang , Yaqi Shi , Yueyang Tan , Ruyu Yan , Jiaqi Chen , Lixing Du , Lu Wang

Speculative decoding (SD) has proven effective for accelerating LLM inference by quickly generating draft tokens and verifying them in parallel. However, SD remains largely unexplored for Large Vision-Language Models (LVLMs), which extend…

Machine Learning · Computer Science 2026-01-29 Minjae Lee , Wonjun Kang , Byeongkeun Ahn , Christian Classen , Kevin Galim , Seunghyuk Oh , Minghao Yan , Hyung Il Koo , Kangwook Lee

Speculative decoding improves LLM inference by generating and verifying multiple tokens in parallel, but existing systems suffer from suboptimal performance due to a mismatch between dynamic speculation and static runtime assumptions. We…

Machine Learning · Computer Science 2026-01-01 Yue Guan , Changming Yu , Shihan Fang , Weiming Hu , Zaifeng Pan , Zheng Wang , Zihan Liu , Yangjie Zhou , Yufei Ding , Minyi Guo , Jingwen Leng

As the usage of large language models (LLMs) grows, performing efficient inference with these models becomes increasingly important. While speculative decoding has recently emerged as a promising direction for speeding up inference,…

Computation and Language · Computer Science 2025-07-08 Zhuoming Chen , Avner May , Ruslan Svirschevski , Yuhsun Huang , Max Ryabinin , Zhihao Jia , Beidi Chen

LLMs have low GPU efficiency and high latency due to autoregressive decoding. Speculative decoding (SD) mitigates this using a small draft model to speculatively generate multiple tokens, which are then verified in parallel by a target…

Computation and Language · Computer Science 2026-04-21 Sungkyun Kim , Jaemin Kim , Dogyung Yoon , Jiho Shin , Junyeol Lee , Jiwon Seo

Autoregressive decoding makes the inference of Large Language Models (LLMs) time-consuming. In this paper, we reconsider speculative sampling and derive two key observations. Firstly, autoregression at the feature (second-to-top-layer)…

Machine Learning · Computer Science 2025-03-05 Yuhui Li , Fangyun Wei , Chao Zhang , Hongyang Zhang

Inference time latency has remained an open challenge for real world applications of large language models (LLMs). State-of-the-art (SOTA) speculative sampling (SpS) methods for LLMs, like EAGLE-3, use tree-based drafting to explore…

Machine Learning · Computer Science 2026-01-21 Chenan Wang , Daniel H. Shi , Haipeng Chen

Speculative generation has emerged as a promising technique to accelerate inference in large language models (LLMs) by leveraging parallelism to verify multiple draft tokens simultaneously. However, the fundamental limits on the achievable…

Computation and Language · Computer Science 2025-12-15 Sergey Pankratov , Dan Alistarh

Speculative decoding accelerates large language model inference by drafting multiple candidate tokens and verifying them in a single forward pass. Candidates are organized as a tree: deeper trees accept more tokens per step, but adding…

Computation and Language · Computer Science 2026-04-03 Tao Jin , Phuong Minh Nguyen , Naoya Inoue

This research aims to accelerate the inference speed of large language models (LLMs) with billions of parameters. We propose \textbf{S}mart \textbf{P}arallel \textbf{A}uto-\textbf{C}orrect d\textbf{E}coding (SPACE), an innovative approach…

Computation and Language · Computer Science 2024-05-21 Hanling Yi , Feng Lin , Hongbin Li , Peiyang Ning , Xiaotian Yu , Rong Xiao