English
Related papers

Related papers: SkipDecode: Autoregressive Skip Decoding with Batc…

200 papers

Large language models (LLMs) rely on key-value cache (KV cache) to accelerate decoding by reducing redundant computations. However, the KV cache memory usage grows substantially with longer text sequences, posing challenges for efficient…

Computation and Language · Computer Science 2025-11-18 Yixuan Wang , Shiyu Ji , Yijun Liu , Yuzhuang Xu , Yang Xu , Qingfu Zhu , Wanxiang Che

Early exiting has recently emerged as a promising technique for accelerating large language models (LLMs) by effectively reducing the hardware computation and memory access. In this paper, we present SpecEE, a fast LLM inference engine with…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-04-15 Jiaming Xu , Jiayi Pan , Yongkang Zhou , Siming Chen , Jinhao Li , Yaoxiu Lian , Junyi Wu , Guohao Dai

Transformer-based large language models (LLMs) rely on key-value (KV) caching to avoid redundant computation during autoregressive inference. While this mechanism greatly improves efficiency, the cache size grows linearly with the input…

Machine Learning · Computer Science 2026-03-12 Jinwoo Ahn , Ingyu Seong , Akhil Kedia , Junhan Kim , Hyemi Jang , Kangwook Lee , Yongkweon Jeon

Decoding strategies play a central role in shaping the reasoning ability of large language models (LLMs). Traditional methods such as greedy decoding and beam search often suffer from error propagation, while sampling-based approaches…

Cost of serving large language models (LLM) is high, but the expensive and scarce GPUs are poorly efficient when generating tokens sequentially, unless the batch of sequences is enlarged. However, the batch size is limited by some…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-03-19 Jiaao He , Jidong Zhai

During inference for transformer-based large language models (LLM), prefilling is the computation of the key-value (KV) cache for input tokens in the prompt prior to autoregressive generation. For longer input prompt lengths, prefilling…

Machine Learning · Computer Science 2024-04-16 Siyan Zhao , Daniel Israel , Guy Van den Broeck , Aditya Grover

Large language models (LLMs) have demonstrated remarkable capabilities across various tasks. However, their widespread application is hindered by the resource-intensive decoding process. To address this challenge, current approaches have…

Computation and Language · Computer Science 2024-04-19 Ziqian Zeng , Jiahong Yu , Qianshi Pang , Zihao Wang , Huiping Zhuang , Hongen Shao , Xiaofeng Zou

KV cache eviction has emerged as an effective solution to alleviate resource constraints faced by LLMs in long-context scenarios. However, existing token-level eviction methods often overlook two critical aspects: (1) their irreversible…

Machine Learning · Computer Science 2026-01-21 Yi Zhao , Yajuan Peng , Cam-Tu Nguyen , Zuchao Li , Xiaoliang Wang , Hai Zhao , Xiaoming Fu

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…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-06-16 Ziyi Zhang , Ziheng Jiang , Chengquan Jiang , Menghan Yu , Size Zheng , Haibin Lin , Henry Hoffmann , Xin Liu

The proliferation of long-context large language models (LLMs) exposes a key bottleneck: the rapidly expanding key-value cache during decoding, which imposes heavy memory and latency costs. While recent approaches attempt to alleviate this…

Computation and Language · Computer Science 2026-02-05 Gang Lin , Dongfang Li , Zhuoen Chen , Yukun Shi , Xuhui Chen , Baotian Hu , Min Zhang

The vast size of Large Language Models (LLMs) has prompted a search to optimize inference. One effective approach is dynamic inference, which adapts the architecture to the sample-at-hand to reduce the overall computational cost. We…

Computation and Language · Computer Science 2024-10-29 Theodore Glavas , Joud Chataoui , Florence Regol , Wassim Jabbour , Antonios Valkanas , Boris N. Oreshkin , Mark Coates

Large language models (LLMs) utilize key-value (KV) cache to store historical information during sequence processing. The size of KV cache grows linearly as the length of the sequence extends, which seriously affects memory usage and…

Computation and Language · Computer Science 2026-01-16 Yijun Liu , Yixuan Wang , Yuzhuang Xu , Shiyu Ji , Yang Xu , Qingfu Zhu , Wanxiang Che

Large Language Models (LLMs) have achieved remarkable performance across a wide variety of natural language tasks; however, their large size makes their inference slow and computationally expensive. Focusing on this problem, we propose to…

Computation and Language · Computer Science 2023-11-08 Neeraj Varshney , Agneet Chatterjee , Mihir Parmar , Chitta Baral

Intermediate-layer predictions in large language models (LLMs) are informative but hard to decode accurately, especially at early layers. Existing lens-style methods typically rely on direct linear readout, which is simple but often drifts…

Computation and Language · Computer Science 2026-03-17 Ming Ma , Bowen Zheng , Zhongqiao Lin , Tianming Yang

One of the most striking findings in modern research on large language models (LLMs) is that scaling up compute during training leads to better results. However, less attention has been given to the benefits of scaling compute during…

Computation and Language · Computer Science 2024-11-21 Sean Welleck , Amanda Bertsch , Matthew Finlayson , Hailey Schoelkopf , Alex Xie , Graham Neubig , Ilia Kulikov , Zaid Harchaoui

Large language model (LLM) decoding involves generating a sequence of tokens based on a given context, where each token is predicted one at a time using the model's learned probabilities. The typical autoregressive decoding method requires…

Computation and Language · Computer Science 2024-08-20 Xukun Liu , Bowen Lei , Ruqi Zhang , Dongkuan Xu

Large Language Model or LLM inference has two phases, the prompt (or prefill) phase to output the first token and the extension (or decoding) phase to the generate subsequent tokens. In this work, we propose an efficient parallelization…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-05-15 Minsik Cho , Mohammad Rastegari , Devang Naik

To tackle the high inference latency exhibited by autoregressive language models, previous studies have proposed an early-exiting framework that allocates adaptive computation paths for each token based on the complexity of generating the…

Computation and Language · Computer Science 2023-10-10 Sangmin Bae , Jongwoo Ko , Hwanjun Song , Se-Young Yun

Large Language Models (LLMs) exhibit enhanced capabilities by Chain-of-Thought reasoning. However, the extended reasoning sequences introduce significant GPU memory overhead due to increased key-value (KV) cache. Existing KV cache…

Machine Learning · Computer Science 2025-10-16 Haoyue Zhang , Hualei Zhang , Xiaosong Ma , Jie Zhang , Song Guo

Early-Exit (EE) is a Large Language Model (LLM) architecture that accelerates inference by allowing easier tokens to be generated using only a subset of the model's layers. However, traditional batching frameworks are ill-suited for EE…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-18 Xuting Liu , Daniel Alexander , Siva Kesava Reddy Kakarla , Behnaz Arzani , Vincent Liu