English
Related papers

Related papers: SIMPLE: Disaggregating Sampling from GPU Inference…

200 papers

We propose XPipe, an efficient asynchronous pipeline model parallelism approach for multi-GPU DNN training. XPipe is designed to use multiple GPUs to concurrently and continuously train different parts of a DNN model. To improve GPU…

Machine Learning · Computer Science 2020-11-10 Lei Guan , Wotao Yin , Dongsheng Li , Xicheng Lu

In this work, we present a new approach to high level synthesis (HLS), where high level functions are first mapped to an architectural template, before hardware synthesis is performed. As FPGA platforms are especially suitable for…

Hardware Architecture · Computer Science 2016-06-22 Shaoyi Cheng , John Wawrzynek

Diffusion-based generation is increasingly powering production content pipelines; however, deploying these models at scale remains a significant challenge. Model weights frequently exceed the memory capacity of commodity GPUs, while the…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-26 Hantian Zha , Teng Ma , Yang Yong , Haiwen Fu , Ruiyang Ma , Wei Gao , Ruihao Gong , Xianglong Liu , Wei Wang , Yunpeng Chai

Disaggregating the prefill and decoding phases represents an effective new paradigm for generative inference of large language models (LLM), which eliminates prefill-decoding interference and optimizes resource allocation. However, it is…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-02-13 Youhe Jiang , Ran Yan , Binhang Yuan

Speculative decoding has emerged as a promising technique for large language model (LLM) inference by accelerating autoregressive decoding via draft-then-verify. This paper studies a new edge scenario with multi-user inference, where draft…

Information Theory · Computer Science 2026-04-24 Yaodan Xu , Sheng Zhou , Zhisheng Niu

Fine-grained workload and resource balancing is the key to high performance for regular and irregular computations on the GPUs. In this dissertation, we conduct an extensive survey of existing load-balancing techniques to build an…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-12-20 Muhammad Osama

Sequential models achieve state-of-the-art results in audio, visual and textual domains with respect to both estimating the data distribution and generating high-quality samples. Efficient sampling for this class of models has however…

Tabular data synthesis is crucial in machine learning, yet existing general methods-primarily based on statistical or deep learning models-are highly data-dependent and often fall short in recommender systems. This limitation arises from…

Information Retrieval · Computer Science 2025-02-12 Jingtong Gao , Zhaocheng Du , Xiaopeng Li , Yichao Wang , Xiangyang Li , Huifeng Guo , Ruiming Tang , Xiangyu Zhao

Evaluating LLMs and text-to-image models is a computationally intensive task often overlooked. Efficient evaluation is crucial for understanding the diverse capabilities of these models and enabling comparisons across a growing number of…

Large Language Models (LLMs) can enhance reasoning capabilities through test-time scaling by generating multiple traces. However, the combination of lengthy reasoning traces with multiple sampling introduces substantial computation and high…

Machine Learning · Computer Science 2026-04-29 Zhixiang Liang , Beichen Huang , Zheng Wang , Minjia Zhang

Large Language Model (LLM) inference is increasingly constrained by GPU memory capacity rather than compute throughput, driven by growing model sizes and the linear growth of the key-value (KV) cache during autoregressive decoding. Existing…

Machine Learning · Computer Science 2026-02-03 Nikhil Gopal , Kostis Kaffes

Fine-tuning large language models (LLMs) requires significant memory, often exceeding the capacity of a single GPU. A common solution to this memory challenge is offloading compute and data from the GPU to the CPU. However, this approach is…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-02-11 Siyuan Chen , Zhuofeng Wang , Zelong Guan , Yudong Liu , Phillip B. Gibbons

Speculative sampling has emerged as an important technique for accelerating the auto-regressive generation process of large language models (LLMs) by utilizing a draft-then-verify mechanism to produce multiple tokens per forward pass. While…

Computation and Language · Computer Science 2025-03-12 Weilin Zhao , Tengyu Pan , Xu Han , Yudi Zhang , Ao Sun , Yuxiang Huang , Kaihuo Zhang , Weilun Zhao , Yuxuan Li , Jianyong Wang , Zhiyuan Liu , Maosong Sun

Despite the remarkable success of large language models (LLMs) on traditional natural language processing tasks, their planning ability remains a critical bottleneck in tackling complex multi-step reasoning tasks. Existing approaches mainly…

Computation and Language · Computer Science 2024-10-07 Jiaxin Wen , Jian Guan , Hongning Wang , Wei Wu , Minlie Huang

With the fast growth of parameter size, it becomes increasingly challenging to deploy large generative models as they typically require large GPU memory consumption and massive computation. Unstructured model pruning has been a common…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-09-20 Haojun Xia , Zhen Zheng , Yuchao Li , Donglin Zhuang , Zhongzhu Zhou , Xiafei Qiu , Yong Li , Wei Lin , Shuaiwen Leon Song

Speculative Decoding (SD) accelerates inference in large language models by using a smaller draft model to propose tokens, which are then verified by a larger target model. However, the throughput gains of SD are fundamentally limited by a…

Computation and Language · Computer Science 2025-10-16 Sanghyun Byun , Mohanad Odema , Jung Ick Guack , Baisub Lee , Jacob Song , Woo Seong Chung

Processing large point clouds is a challenging task. Therefore, the data is often sampled to a size that can be processed more easily. The question is how to sample the data? A popular sampling technique is Farthest Point Sampling (FPS).…

Computer Vision and Pattern Recognition · Computer Science 2019-04-02 Oren Dovrat , Itai Lang , Shai Avidan

Lazy search algorithms have been developed to efficiently solve planning problems in domains where the computational effort is dominated by the cost of edge evaluation. The existing algorithms operate by intelligently balancing…

Robotics · Computer Science 2023-01-16 Shohin Mukherjee , Sandip Aine , Maxim Likhachev

Capturing complex user preferences from sparse behavioral sequences remains a fundamental challenge in sequential recommendation. Recent latent reasoning methods have shown promise by extending test-time computation through multi-step…

Information Retrieval · Computer Science 2026-01-07 Jiakai Tang , Xu Chen , Wen Chen , Jian Wu , Yuning Jiang , Bo Zheng

Large Language Models (LLMs) have recently made significant advances in code generation through the 'Chain-of-Thought' prompting technique. This technique empowers the model to autonomously devise "solution plans" to tackle intricate…

Software Engineering · Computer Science 2024-03-21 Zhihong Sun , Chen Lyu , Bolun Li , Yao Wan , Hongyu Zhang , Ge Li , Zhi Jin