English
Related papers

Related papers: Prefill-Decode Aggregation or Disaggregation? Unif…

200 papers

In multi-model LLM serving, decode execution remains inefficient due to model-specific resource partitioning: since cross-model batching is not possible, memory-bound decoding often suffers from severe GPU underutilization, especially under…

Artificial Intelligence · Computer Science 2026-03-04 Sunghyeon Woo , Ahreum Seo , Jaegwang Lee , Jaeeun Kil , Hanbae Seo , Joonghoon Kim , Baeseong Park , Se Jung Kwon , Dongsoo Lee

Large language models (LLMs) have transformed natural language processing but face critical deployment challenges in device-edge systems due to resource limitations and communication overhead. To address these issues, collaborative…

Signal Processing · Electrical Eng. & Systems 2025-07-18 Jiahong Ning , Ce Zheng , Tingting Yang

This paper presents an efficient decoding approach for end-to-end automatic speech recognition (E2E-ASR) with large language models (LLMs). Although shallow fusion is the most common approach to incorporate language models into E2E-ASR…

Computation and Language · Computer Science 2025-01-17 Takaaki Hori , Martin Kocour , Adnan Haider , Erik McDermott , Xiaodan Zhuang

Test-Time Scaling (TTS) improves the reasoning performance of Large Language Models (LLMs) by allocating additional compute during inference. We conduct a structured survey of TTS methods and categorize them into sampling-based,…

Computation and Language · Computer Science 2025-06-06 Ho-Lam Chung , Teng-Yun Hsiao , Hsiao-Ying Huang , Chunerh Cho , Jian-Ren Lin , Zhang Ziwei , Yun-Nung Chen

Visual-Language Models (VLMs), with their strong capabilities in image and text understanding, offer a solid foundation for intelligent communications. However, their effectiveness is constrained by limited token granularity, overlong…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Feibo Jiang , Siwei Tu , Li Dong , Xiaolong Li , Kezhi Wang , Cunhua Pan , Zhu Han , Jiangzhou Wang

Training large language models (LLMs) is often constrained by GPU memory limitations. To alleviate memory pressure, activation recomputation and data compression have been proposed as two major strategies. However, both approaches have…

Machine Learning · Computer Science 2025-08-11 Ping Chen , Zhuohong Deng , Ping Li , Shuibing He , Hongzi Zhu , Yi Zheng , Zhefeng Wang , Baoxing Huai , Minyi Guo

The growth in the number of parameters of Large Language Models (LLMs) has led to a significant surge in computational requirements, making them challenging and costly to deploy. Speculative decoding (SD) leverages smaller models to…

Computation and Language · Computer Science 2025-04-04 Matthieu Zimmer , Milan Gritta , Gerasimos Lampouras , Haitham Bou Ammar , Jun Wang

The code generation capabilities of Large Language Models (LLMs) have advanced applications like tool invocation and problem-solving. However, improving performance in code-related tasks remains challenging due to limited training data that…

Computation and Language · Computer Science 2025-08-28 Houxing Ren , Zimu Lu , Weikang Shi , Haotian Hou , Yunqiao Yang , Ke Wang , Aojun Zhou , Junting Pan , Mingjie Zhan , Hongsheng Li

Process reward models (PRMs) are a cornerstone of test-time scaling (TTS), designed to verify and select the best responses from large language models (LLMs). However, this promise is challenged by recent benchmarks where simple majority…

Computation and Language · Computer Science 2026-04-24 Peng Kuang , Yanli Wang , Xiaoyu Han , Yaowenqi Liu , Kaidi Xu , Haohan Wang

Existing LLM serving strategies can be categorized based on whether prefill and decode phases are disaggregated: non-disaggregated (NoDG) or fully disaggregated (FuDG). However, the NoDG strategy leads to strong prefill-decode interference…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-04-28 Jiangsu Du , Hongbin Zhang , Taosheng Wei , Zhenyi Zheng , Kaiyi Wu , Zhiguang Chen , Yutong Lu

Large language models (LLMs) exhibit complementary strengths arising from differences in pretraining data, model architectures, and decoding behaviors. Inference-time ensembling provides a practical way to combine these capabilities without…

Computation and Language · Computer Science 2026-01-12 Chengming Cui , Tianxin Wei , Ziyi Chen , Ruizhong Qiu , Zhichen Zeng , Zhining Liu , Xuying Ning , Duo Zhou , Jingrui He

Scaling distributed training of Large Language Models (LLMs) requires not only algorithmic advances but also efficient utilization of heterogeneous hardware resources. While existing methods such as DiLoCo have demonstrated promising…

Multimodal large language models (MLLMs) extend LLMs with visual understanding through a three-stage pipeline: multimodal preprocessing, vision encoding, and LLM inference. While these stages enhance capability, they introduce significant…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-22 Lingxiao Zhao , Haoran Zhou , Yuezhi Che , Dazhao Cheng

Multimodal learning often encounters the under-optimized problem and may have worse performance than unimodal learning. Existing methods attribute this problem to the imbalanced learning between modalities and rebalance them through…

Computer Vision and Pattern Recognition · Computer Science 2025-07-15 Shicai Wei , Chunbo Luo , Yang Luo

We study a mismatch between the deep learning recommendation models' flat architecture, common distributed training paradigm and hierarchical data center topology. To address the associated inefficiencies, we propose Disaggregated…

The growth of Large Language Models (LLMs) has necessitated large-scale distributed training. Highly optimized frameworks, however, still suffer significant losses in Model FLOPS utilization (often below 50%) due to large communication…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-11-26 Haiquan Wang , Chaoyi Ruan , Jia He , Jiaqi Ruan , Chengjie Tang , Xiaosong Ma , Cheng Li

Multimodal large language models (LLMs) empower LLMs to ingest inputs and generate outputs in multiple forms, such as text, image, and audio. However, the integration of multiple modalities introduces heterogeneity in both the model and…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-01 Zili Zhang , Yinmin Zhong , Yimin Jiang , Hanpeng Hu , Jianjian Sun , Zheng Ge , Yibo Zhu , Daxin Jiang , Xin Jin

Parameter-Efficient Fine-Tuning (PEFT) is essential for adapting Large Language Models (LLMs). In practice, LLMs are often required to handle a diverse set of tasks from multiple domains, a scenario naturally addressed by multi-task…

Computation and Language · Computer Science 2025-08-08 Jinda Liu , Bo Cheng , Yi Chang , Yuan Wu

Recent advancements in Large Language Models (LLMs) have transformed many fields including scientific discovery, content generation, biomedical text mining, and educational technology. However, the substantial requirements for training…

Machine Learning · Computer Science 2025-08-05 Yigit Turkmen , Baturalp Buyukates , Melih Bastopcu

Large language models (LLMs) have significantly advanced the natural language processing paradigm but impose substantial demands on memory and computational resources. Quantization is one of the most effective ways to reduce memory…

Machine Learning · Computer Science 2025-04-29 Xilong Xie , Liang Wang , Limin Xiao , Meng Han , Lin Sun , Shuai Zheng , Xiangrong Xu
‹ Prev 1 4 5 6 7 8 10 Next ›