English
Related papers

Related papers: Mamba Drafters for Speculative Decoding

200 papers

State-space models (SSMs) have recently demonstrated competitive performance to transformers at large-scale language modeling benchmarks while achieving linear time and memory complexity as a function of sequence length. Mamba, a recently…

Computation and Language · Computer Science 2024-02-06 Quentin Anthony , Yury Tokpanov , Paolo Glorioso , Beren Millidge

Speculative decoding (SD) is a promising method for accelerating the decoding process of Large Language Models (LLMs). The efficiency of SD primarily hinges on the consistency between the draft model and the verify model. However, existing…

Computation and Language · Computer Science 2025-06-02 Longze Chen , Renke Shan , Huiming Wang , Lu Wang , Ziqiang Liu , Run Luo , Jiawei Wang , Hamid Alinejad-Rokny , Min Yang

Long-range sequence processing poses a significant challenge for Transformers due to their quadratic complexity in input length. A promising alternative is Mamba, which demonstrates high performance and achieves Transformer-level…

Machine Learning · Computer Science 2025-04-11 Assaf Ben-Kish , Itamar Zimerman , Shady Abu-Hussein , Nadav Cohen , Amir Globerson , Lior Wolf , Raja Giryes

Sequence models like Transformers and RNNs often overallocate attention to irrelevant context, leading to noisy intermediate representations. This degrades LLM capabilities by promoting hallucinations, weakening long-range and retrieval…

Machine Learning · Computer Science 2025-10-30 Nadav Schneider , Itamar Zimerman , Eliya Nachmani

The typical Selective State-Space Model (SSM) used in Mamba addresses several limitations of Transformers, such as the quadratic computational complexity with respect to sequence length and the significant memory requirements during…

Computation and Language · Computer Science 2025-10-24 Shengkun Tang , Liqun Ma , Haonan Li , Mingjie Sun , Zhiqiang Shen

Speculative decoding, which combines a draft model with a target model, has emerged as an effective approach to accelerate large language model (LLM) inference. However, existing methods often face a trade-off between the acceptance rate…

Computation and Language · Computer Science 2025-05-14 Danying Ge , Jianhua Gao , Qizhi Jiang , Yifei Feng , Weixing Ji

Motion prediction is crucial for autonomous driving, as it enables accurate forecasting of future vehicle trajectories based on historical inputs. This paper introduces Trajectory Mamba, a novel efficient trajectory prediction framework…

Computer Vision and Pattern Recognition · Computer Science 2025-03-17 Yizhou Huang , Yihua Cheng , Kezhi Wang

The emergence of long-context large language models (LLMs) offers a promising alternative to traditional retrieval-augmented generation (RAG) for processing extensive documents. However, the computational overhead of long-context inference…

Computation and Language · Computer Science 2025-06-24 Guanzheng Chen , Qilong Feng , Jinjie Ni , Xin Li , Michael Qizhe Shieh

Speculative decoding has emerged as a promising approach to accelerate autoregressive inference in large language models (LLMs). Self-draft methods, which leverage the base LLM itself for speculation, avoid the overhead of auxiliary draft…

Computation and Language · Computer Science 2026-04-15 Zhuofan Wen , Yang Feng

Speculative decoding is an inference-acceleration method for large language models (LLMs) where a small language model generates a draft-token sequence which is further verified by the target LLM in parallel. Recent works have advanced this…

Machine Learning · Computer Science 2024-03-06 Wonseok Jeon , Mukul Gagrani , Raghavv Goel , Junyoung Park , Mingu Lee , Christopher Lott

Mamba-based State Space Models (SSM) have emerged as a promising alternative to the ubiquitous transformers. Despite the expressive power of transformers, the quadratic complexity of computing attention is a major impediment to scaling…

Machine Learning · Computer Science 2025-08-26 Trinayan Baruah , Kaustubh Shivdikar , Sara Prescott , David Kaeli

Large language models (LLMs) have shown outstanding performance across numerous real-world tasks. However, the autoregressive nature of these models makes the inference process slow and costly. Speculative decoding has emerged as a…

Artificial Intelligence · Computer Science 2025-03-17 Zongyue Qin , Zifan He , Neha Prakriya , Jason Cong , Yizhou Sun

Transformers are the current architecture of choice for NLP, but their attention layers do not scale well to long contexts. Recent works propose to replace attention with linear recurrent layers -- this is the case for state space models,…

Computation and Language · Computer Science 2024-07-09 Hugo Pitorro , Pavlo Vasylenko , Marcos Treviso , André F. T. Martins

This study explores replacing Transformers in Visual Language Models (VLMs) with Mamba, a recent structured state space model (SSM) that demonstrates promising performance in sequence modeling. We test models up to 3B parameters under…

Computer Vision and Pattern Recognition · Computer Science 2024-10-02 Georgios Pantazopoulos , Malvina Nikandrou , Alessandro Suglia , Oliver Lemon , Arash Eshghi

Speculative decoding has rapidly emerged as a leading approach for accelerating language model (LM) inference, as it offers substantial speedups while yielding identical outputs. This relies upon a small draft model, tasked with predicting…

Computation and Language · Computer Science 2026-02-17 Miles Williams , Young D. Kwon , Rui Li , Alexandros Kouris , Stylianos I. Venieris

Inference acceleration of large language models (LLMs) has been put forward in many application scenarios and speculative decoding has shown its advantage in addressing inference acceleration. Speculative decoding usually introduces a draft…

Machine Learning · Computer Science 2024-12-03 Zhuofan Wen , Shangtong Gui , Yang Feng

In scene text detection, Transformer-based methods have addressed the global feature extraction limitations inherent in traditional convolution neural network-based methods. However, most directly rely on native Transformer attention layers…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Qiyan Zhao , Yue Yan , Da-Han Wang

State space models (SSMs), such as Mamba, have emerged as an efficient alternative to transformers for long-context sequence modeling. However, despite their growing adoption, SSMs lack the interpretability tools that have been crucial for…

Computation and Language · Computer Science 2025-02-26 Hugo Pitorro , Marcos Treviso

Current automatic speech recognition systems struggle with modeling long speech sequences due to high quadratic complexity of Transformer-based models. Selective state space models such as Mamba has performed well on long-sequence modeling…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-30 Xiaoxue Gao , Nancy F. Chen

Transformers have revolutionized deep learning across various tasks, including audio representation learning, due to their powerful modeling capabilities. However, they often suffer from quadratic complexity in both GPU memory usage and…

Audio and Speech Processing · Electrical Eng. & Systems 2025-02-06 Siavash Shams , Sukru Samet Dindar , Xilin Jiang , Nima Mesgarani