English
Related papers

Related papers: NEZHA: A Zero-sacrifice and Hyperspeed Decoding Ar…

200 papers

Large language models and large multimodal models (LLMs and LMMs) deliver strong generative performance but suffer from slow decoding, a problem that becomes more severe when handling visual inputs, whose sequences typically contain many…

Computer Vision and Pattern Recognition · Computer Science 2026-02-04 Zihua Wang , Ruibo Li , Haozhe Du , Joey Tianyi Zhou , Yu Zhang , Xu Yang

Large Language Models (LLMs) employ auto-regressive decoding that requires sequential computation, with each step reliant on the previous one's output. This creates a bottleneck as each step necessitates moving the full model parameters…

Machine Learning · Computer Science 2024-06-18 Tianle Cai , Yuhong Li , Zhengyang Geng , Hongwu Peng , Jason D. Lee , Deming Chen , Tri Dao

Speculative decoding accelerates large language model (LLM) inference by using a lightweight draft model to propose tokens that are later verified by a stronger target model. While effective in centralized systems, its behavior in…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-18 Jingwei Song , Wanyi Chen , Xinyuan Song , Max , Chris Tong , Gufeng Chen , Tianyi Zhao , Eric Yang , Bill Shi , Lynn Ai

Recommender Systems (RSs) have become the cornerstone of various applications such as e-commerce and social media platforms. The evolution of RSs is paramount in the digital era, in which personalised user experience is tailored to the…

Information Retrieval · Computer Science 2025-12-09 Tendai Mukande , Esraa Ali , Annalina Caputo , Ruihai Dong , Noel OConnor

We propose an acceleration scheme for large language models (LLMs) through Speculative Decoding with Semantic Adaptive Tokens (SDSAT). The primary objective of this design is to enhance the LLM model's ability to generate draft tokens more…

Computation and Language · Computer Science 2024-04-02 Chengbo Liu , Yong Zhu

Speculative decoding (SD), where a draft model provides multiple candidate tokens for the target model to verify in parallel, has demonstrated significant potential for accelerating LLM inference. Yet, existing SD approaches adhere to a…

Machine Learning · Computer Science 2025-09-22 Enyu Zhou , Kai Sheng , Hao Chen , Xin He

End-to-end automatic speech recognition (ASR) systems based on transformer architectures, such as Whisper, offer high transcription accuracy and robustness. However, their autoregressive decoding is computationally expensive, hence limiting…

Computation and Language · Computer Science 2025-07-30 Tuan Vu Ho , Hiroaki Kokubo , Masaaki Yamamoto , Yohei Kawaguchi

We propose a new, training-free method, Graph Reasoning via Retrieval Augmented Framework (GRRAF), that harnesses retrieval-augmented generation (RAG) alongside the code-generation capabilities of large language models (LLMs) to address a…

Artificial Intelligence · Computer Science 2025-09-17 Hanqing Li , Kiran Sheena Jyothi , Henry Liang , Sharika Mahadevan , Diego Klabjan

Retrieval-Augmented Generation (RAG) improves Large Language Model (LLM) performance on knowledge-intensive tasks but depends heavily on initial search query quality. Current methods, often using Reinforcement Learning (RL), typically focus…

Computation and Language · Computer Science 2025-04-16 Alan Dao , Thinh Le

We present ErasureHead, a new approach for distributed gradient descent (GD) that mitigates system delays by employing approximate gradient coding. Gradient coded distributed GD uses redundancy to exactly recover the gradient at each…

Machine Learning · Computer Science 2019-01-29 Hongyi Wang , Zachary Charles , Dimitris Papailiopoulos

Query rewriting is pivotal for enhancing dense retrieval, yet current methods demand large-scale supervised data or suffer from inefficient reinforcement learning (RL) exploration. In this work, we first establish that guiding Large…

Artificial Intelligence · Computer Science 2025-07-29 Teng Wang , Hailei Gong , Changwang Zhang , Jun Wang

We investigate nonlinear prediction in an online setting and introduce a hybrid model that effectively mitigates, via an end-to-end architecture, the need for hand-designed features and manual model selection issues of conventional…

Machine Learning · Statistics 2023-07-11 Mustafa E. Aydın , Suleyman S. Kozat

Large Language Models (LLMs) inherently use autoregressive decoding, which lacks parallelism in inference and results in significantly slow inference speed. While methods such as Medusa constructs parallelized heads, they lack adequate…

Artificial Intelligence · Computer Science 2024-10-21 Zeping Li , Xinlong Yang , Ziheng Gao , Ji Liu , Guanchen Li , Zhuang Liu , Dong Li , Jinzhang Peng , Lu Tian , Emad Barsoum

Serving generative inference of the large language model is a crucial component of contemporary AI applications. This paper focuses on deploying such services in a heterogeneous and cross-datacenter setting to mitigate the substantial…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-05-28 Youhe Jiang , Ran Yan , Xiaozhe Yao , Yang Zhou , Beidi Chen , Binhang Yuan

Autoregressive decoding in Large Language Models (LLMs) generates one token per step, causing high inference latency. Speculative decoding (SD) mitigates this through a guess-and-verify strategy, but existing training-free variants face…

Computation and Language · Computer Science 2026-04-17 Zihong Zhang , Zuchao Li , Lefei Zhang , Ping Wang , Hai Zhao

Speculative decoding speeds up autoregressive generation in Large Language Models (LLMs) through a two-step procedure, where a lightweight draft model proposes tokens which the target model then verifies in a single forward pass. Although…

Machine Learning · Computer Science 2026-05-12 Anton Plaksin , Sergei Krutikov , Sergei Skvortsov , Alexander Samarin

To combat the memory bandwidth-bound nature of autoregressive LLM inference, previous research has proposed the speculative decoding frame-work. To perform speculative decoding, a small draft model proposes candidate continuations of the…

Speculative decoding accelerates inference in large language models (LLMs) by generating draft tokens for target model verification. Current approaches for obtaining draft tokens rely on lightweight draft models or additional model…

Computation and Language · Computer Science 2025-03-06 Guofeng Quan , Wenfeng Feng , Chuzhan Hao , Guochao Jiang , Yuewei Zhang , Hao Wang

Large language models achieve strong machine translation quality but incur high inference cost and latency, posing challenges for simultaneous translation. Re-translation provides a practical solution for off-the-shelf LLMs by repeatedly…

Computation and Language · Computer Science 2026-01-06 Linxiao Zeng , Haoyun Deng , Kangyuan Shu , Shizhen Wang

Many applications today provide users with multiple auto-complete drafts as they type, including GitHub's code completion, Gmail's smart compose, and Apple's messaging auto-suggestions. Under the hood, language models support this by…