中文
相关论文

相关论文: Speculate Deep and Accurate: Lossless and Training…

200 篇论文

As Large Language Models (LLMs) can now process extremely long contexts, efficient inference over these extended inputs has become increasingly important, especially for emerging applications like LLM agents that highly depend on this…

计算与语言 · 计算机科学 2026-04-09 Penghui Yang , Cunxiao Du , Fengzhuo Zhang , Haonan Wang , Tianyu Pang , Chao Du , Bo An

Self-speculative decoding (SSD) accelerates LLM inference by skipping layers to create an efficient draft model, yet existing methods often rely on static heuristics that ignore the dynamic computational overhead of attention in…

机器学习 · 计算机科学 2026-02-25 Seongjin Cha , Gyuwan Kim , Dongsu Han , Tao Yang , Insu Han

Speculative decoding is a widely adopted technique for accelerating inference in large language models (LLMs), yet its application to vision-language models (VLMs) remains underexplored, with existing methods achieving only modest speedups…

计算机视觉与模式识别 · 计算机科学 2025-10-24 Jialiang Kang , Han Shu , Wenshuo Li , Yingjie Zhai , Xinghao Chen

Efficient LLM inference on resource-constrained devices presents significant challenges in compute and memory utilization. Due to limited GPU memory, existing systems offload model weights to CPU memory, incurring substantial I/O overhead…

机器学习 · 计算机科学 2025-05-22 Xiangwen Zhuge , Xu Shen , Zeyu Wang , Fan Dang , Xuan Ding , Danyang Li , Yahui Han , Tianxiang Hao , Zheng Yang

Speculative decoding is an effective and lossless method for Large Language Model (LLM) inference acceleration. It employs a smaller model to generate a draft token sequence, which is then verified by the original base model. In multi-GPU…

机器学习 · 计算机科学 2025-12-09 Yize Wu , Ke Gao , Ling Li , Yanjun Wu

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…

机器学习 · 计算机科学 2026-05-12 Anton Plaksin , Sergei Krutikov , Sergei Skvortsov , Alexander Samarin

Low-latency decoding for large language models (LLMs) is crucial for applications like chatbots and code assistants, yet generating long outputs remains slow in single-query settings. Prior work on speculative decoding (which combines a…

分布式、并行与集群计算 · 计算机科学 2025-06-16 Ziyi Zhang , Ziheng Jiang , Chengquan Jiang , Menghan Yu , Size Zheng , Haibin Lin , Henry Hoffmann , Xin Liu

Quantization is widely adopted to accelerate inference and reduce memory consumption in large language models (LLMs). While activation-weight joint quantization enables efficient low-precision decoding, it suffers from substantial…

机器学习 · 计算机科学 2025-10-03 Juntao Zhao , Wenhao Lu , Sheng Wang , Lingpeng Kong , Chuan Wu

Adapting large language models (LLMs) via reinforcement learning (RL) is often bottlenecked by the generation stage, which can consume over 75\% of the training time. Speculative decoding (SD) accelerates autoregressive generation in…

机器学习 · 计算机科学 2025-10-31 Qiaoling Chen , Zijun Liu , Peng Sun , Shenggui Li , Guoteng Wang , Ziming Liu , Yonggang Wen , Siyuan Feng , Tianwei Zhang

Large Language Models (LLMs) are increasingly being deployed on edge devices for long-context settings, creating a growing need for fast and efficient long-context inference. In these scenarios, the Key-Value (KV) cache is the primary…

Speculative decoding is a prominent technique to speed up the inference of a large target language model based on predictions of an auxiliary draft model. While effective, in application-specific settings, it often involves fine-tuning both…

计算与语言 · 计算机科学 2024-02-20 Nikhil Bhendawade , Irina Belousova , Qichen Fu , Henry Mason , Mohammad Rastegari , Mahyar Najibi

Large language models achieve impressive performance across diverse tasks but exhibit high inference latency due to their large parameter sizes. While quantization reduces model size, it often leads to performance degradation compared to…

硬件体系结构 · 计算机科学 2025-10-22 Yushu Zhao , Yubin Qin , Yang Wang , Xiaolong Yang , Huiming Han , Shaojun Wei , Yang Hu , Shouyi Yin

Speculative decoding accelerates LLM inference by utilizing otherwise idle computational resources during memory-to-chip data transfer. Current speculative decoding methods typically assume a considerable amount of available computing…

计算与语言 · 计算机科学 2025-11-26 Luohe Shi , Zuchao Li , Lefei Zhang , Baoyuan Qi , Guoming Liu , Hai Zhao

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…

计算与语言 · 计算机科学 2026-04-15 Zhuofan Wen , Yang Feng

As large language models gain widespread adoption, running them efficiently becomes crucial. Recent works on LLM inference use speculative decoding to achieve extreme speedups. However, most of these works implicitly design their algorithms…

计算与语言 · 计算机科学 2024-12-03 Ruslan Svirschevski , Avner May , Zhuoming Chen , Beidi Chen , Zhihao Jia , Max Ryabinin

Speculative decoding (SD) has emerged as a method to accelerate LLM inference without sacrificing any accuracy over the 16-bit model inference. In a typical SD setup, the idea is to use a full-precision, small, fast model as "draft" to…

计算与语言 · 计算机科学 2025-03-19 Evangelos Georganas , Dhiraj Kalamkar , Alexander Kozlov , Alexander Heinecke

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.…

计算与语言 · 计算机科学 2025-06-12 Nadav Timor , Jonathan Mamou , Daniel Korat , Moshe Berchansky , Gaurav Jain , Oren Pereg , Moshe Wasserblat , David Harel

Speculative decoding is a widely used technique for accelerating inference in large language models (LLMs), but its performance degrades as input length grows, with significant drops even at moderate lengths. Yet, this early degradation has…

计算与语言 · 计算机科学 2026-01-21 Jungyoub Cha , Hyunjong Kim , Sungzoon Cho

Deployment of autoregressive large language models (LLMs) is costly, and as these models increase in size, the associated costs will become even more considerable. Consequently, different methods have been proposed to accelerate the token…

Speculative decoding has proven to be an efficient solution to large language model (LLM) inference, where the small drafter predicts future tokens at a low cost, and the target model is leveraged to verify them in parallel. However, most…

计算与语言 · 计算机科学 2024-10-10 Zilin Xiao , Hongming Zhang , Tao Ge , Siru Ouyang , Vicente Ordonez , Dong Yu
‹ 上一页 1 2 3 10 下一页 ›