English
Related papers

Related papers: Tandem Transformers for Inference Efficient LLMs

200 papers

The rapid development of large language model (LLM)-based agents has unlocked new possibilities for autonomous multi-turn reasoning and tool-augmented decision-making. However, their real-world deployment is hindered by severe…

Generative Large Language Models (LLMs) have achieved remarkable advancements in various NLP tasks. However, these advances have not been reflected in the translation task, especially those with moderate model sizes (i.e., 7B or 13B…

Computation and Language · Computer Science 2024-02-07 Haoran Xu , Young Jin Kim , Amr Sharaf , Hany Hassan Awadalla

Reasoning-oriented Large Language Models (LLMs) often rely on generating explicit tokens step by step, and their effectiveness typically hinges on large-scale supervised fine-tuning or reinforcement learning. While Chain-of-Thought (CoT)…

Computation and Language · Computer Science 2025-09-30 Haoyu Zheng , Zhuonan Wang , Yuqian Yuan , Tianwei Lin , Wenqiao Zhang , Zheqi Lv , Juncheng Li , Siliang Tang , Yueting Zhuang , Hongyang He

Accelerating the inference of large language models (LLMs) is a critical challenge in generative AI. Speculative decoding (SD) methods offer substantial efficiency gains by generating multiple tokens using a single target forward pass.…

Computation and Language · Computer Science 2025-06-12 Nadav Timor , Jonathan Mamou , Daniel Korat , Moshe Berchansky , Gaurav Jain , Oren Pereg , Moshe Wasserblat , David Harel

Adjusting the latency, power, and accuracy of natural language understanding models is a desirable objective of an efficient architecture. This paper proposes an efficient Transformer architecture that adjusts the inference computational…

Computation and Language · Computer Science 2024-09-20 Sajjad Kachuee , Mohammad Sharifkhani

Large language models (LLMs) have rapidly progressed into general-purpose agents capable of solving a broad spectrum of tasks. However, current models remain inefficient at reasoning: they apply fixed inference-time compute regardless of…

The remarkable success of Chain-of-Thought (CoT), which enhances performance by scaling generation steps at test-time, inspires us to ask: can we leverage a similar scaling of computational steps during pretraining to improve the generation…

Computation and Language · Computer Science 2026-03-10 Boyi Zeng , He Li , Shixiang Song , Yixuan Wang , Zitong Wang , Ziwei He , Xinbing Wang , Zhouhan Lin

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…

Computation and Language · Computer Science 2024-07-24 Zhuocheng Gong , Jiahao Liu , Ziyue Wang , Pengfei Wu , Jingang Wang , Xunliang Cai , Dongyan Zhao , Rui Yan

We present speculative sampling, an algorithm for accelerating transformer decoding by enabling the generation of multiple tokens from each transformer call. Our algorithm relies on the observation that the latency of parallel scoring of…

Computation and Language · Computer Science 2023-02-03 Charlie Chen , Sebastian Borgeaud , Geoffrey Irving , Jean-Baptiste Lespiau , Laurent Sifre , John Jumper

The transition from standard generative AI to \emph{reasoning-centric architectures}, exemplified by models capable of extensive Chain-of-Thought~(CoT) processing, marks a fundamental paradigm shift in system requirements. Unlike…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-20 Moiz Arif , Avinash Maurya , Sudharshan Vazhkudai , Bogdan Nicolae

Transformer based language models (LMs) demonstrate increasing performance with scale across a wide variety of tasks. Scale alone however cannot enable models to solve tasks that require access to ephemeral, changing, or private data that…

Computation and Language · Computer Science 2022-05-25 Aaron Parisi , Yao Zhao , Noah Fiedel

The growing demand for on-device large language model (LLM) inference highlights the need for efficient mobile edge computing (MEC) solutions, especially in resource-constrained settings. Speculative decoding offers a promising solution by…

Machine Learning · Computer Science 2025-12-01 Jungyeon Koh , Hyun Jong Yang

Powerful foundation models, including large language models (LLMs), with Transformer architectures have ushered in a new era of Generative AI across various industries. Industry and research community have witnessed a large number of new…

Large language models such as GPT and Llama are trained with a next-token prediction loss. In this work, we suggest that training language models to predict multiple future tokens at once results in higher sample efficiency. More…

Computation and Language · Computer Science 2026-03-03 Athul Radhakrishnan , Siddhant Mohan , Mahima Sachdeva

Autoregressive (AR) generation is the standard decoding paradigm for Large Language Models (LLMs), but its token-by-token nature limits parallelism at inference time. Diffusion Language Models (DLLMs) offer parallel decoding by recovering…

Computation and Language · Computer Science 2025-12-30 Aiwei Liu , Minghua He , Shaoxun Zeng , Sijun Zhang , Linhao Zhang , Chuhan Wu , Wei Jia , Yuan Liu , Xiao Zhou , Jie Zhou

As large language models (LLMs) have shown great success in many tasks, they are used in various applications. While a lot of works have focused on the efficiency of single-LLM application (e.g., offloading, request scheduling, parallelism…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-03-24 Jingzhi Fang , Yanyan Shen , Yue Wang , Lei Chen

Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to autoregressive (AR) LLMs for text generation, with the potential to decode multiple tokens in a single iteration. However, none of the existing open-source…

Machine Learning · Computer Science 2025-08-14 Xu Wang , Chenkai Xu , Yijie Jin , Jiachun Jin , Hao Zhang , Zhijie Deng

Large language models (LLMs) have achieved near-human performance across diverse reasoning tasks, yet their deployment on resource-constrained Internet-of-Things (IoT) devices remains impractical due to massive parameter footprints and…

Machine Learning · Computer Science 2025-11-07 Mingyu Sung , Vikas Palakonda , Suhwan Im , Sunghwan Moon , Il-Min Kim , Sangseok Yun , Jae-Mo Kang

We present a novel inference scheme, self-speculative decoding, for accelerating Large Language Models (LLMs) without the need for an auxiliary model. This approach is characterized by a two-stage process: drafting and verification. The…

Computation and Language · Computer Science 2025-02-11 Jun Zhang , Jue Wang , Huan Li , Lidan Shou , Ke Chen , Gang Chen , Sharad Mehrotra

Diffusion Large Language Models (DLLMs) offer a compelling alternative to Auto-Regressive models, but their deployment is constrained by high decoding cost. In this work, we identify a key inefficiency in DLLM decoding: while computation is…

Machine Learning · Computer Science 2026-02-02 Kaihua Liang , Xin Tan , An Zhong , Hong Xu , Marco Canini