English
Related papers

Related papers: Optimized Speculative Sampling for GPU Hardware Ac…

200 papers

Gibbs sampling is a widely used Markov chain Monte Carlo (MCMC) method for numerically approximating integrals of interest in Bayesian statistics and other mathematical sciences. Many implementations of MCMC methods do not extend easily to…

Computation · Statistics 2019-06-03 Alexander Terenin , Shawfeng Dong , David Draper

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

Hardware accelerators, such as those based on GPUs and FPGAs, offer an excellent opportunity to efficiently parallelize functionalities. Recently, modern embedded platforms started being equipped with such accelerators, resulting in a…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-05-16 Daniel Casini , Paolo Pazzaglia , Alessandro Biondi , Marco Di Natale

Discrete optimization is a central problem in artificial intelligence. The optimization of the aggregated cost of a network of cost functions arises in a variety of problems including (W)CSP, DCOP, as well as optimization in stochastic…

Artificial Intelligence · Computer Science 2018-01-12 Ferdinando Fioretto , Enrico Pontelli , William Yeoh , Rina Dechter

We propose a generic algorithmic building block to accelerate training of machine learning models on heterogeneous compute systems. Our scheme allows to efficiently employ compute accelerators such as GPUs and FPGAs for the training of…

Machine Learning · Computer Science 2017-11-08 Celestine Dünner , Thomas Parnell , Martin Jaggi

Model comparison and calibrated uncertainty quantification often require integrating over parameters, but scalable inference can be challenging for complex, multimodal targets. Nested Sampling is a robust alternative to standard MCMC, yet…

Computation · Statistics 2026-05-12 David Yallup , Namu Kroupa , Will Handley

We explore how the big-three computing paradigms -- symmetric multi-processor (SMC), graphical processing units (GPUs), and cluster computing -- can together be brought to bare on large-data Gaussian processes (GP) regression problems via a…

Computation · Statistics 2014-06-05 Robert B. Gramacy , Jarad Niemi , Robin M. Weiss

Large Language Models (LLMs) like GPT are state-of-the-art text generation models that provide significant assistance in daily routines. However, LLM execution is inherently sequential, since they only produce one token at a time, thus…

Machine Learning · Computer Science 2023-10-31 Qidong Su , Christina Giannoula , Gennady Pekhimenko

Computational intensity and sequential nature of estimation techniques for Bayesian methods in statistics and machine learning, combined with their increasing applications for big data analytics, necessitate both the identification of…

Computation · Statistics 2015-03-02 Alireza S. Mahani , Mansour T. A. Sharabiani

GPU architectural simulation is orders of magnitude slower than native execution, necessitating workload sampling for practical speedups. Existing methods rely on hand-crafted features with limited expressiveness, yielding either aggressive…

Performance · Computer Science 2026-03-03 Jiaqi Wang , Jingwei Sun , Jiyu Luo , Han Li , Guangzhong Sun

The IEEE 754-2008 standard recommends the correct rounding of some elementary functions. This requires to solve the Table Maker's Dilemma which implies a huge amount of CPU computation time. We consider in this paper accelerating such…

Mathematical Software · Computer Science 2013-06-06 Pierre Fortin , Mourad Gouicem , Stef Graillat

Data summarizations are a valuable tool to derive knowledge from large data streams and have proven their usefulness in a great number of applications. Summaries can be found by optimizing submodular functions. These functions map subsets…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-06-22 Philipp-Jan Honysz , Alexander Schulze-Struchtrup , Sebastian Buschjäger , Katharina Morik

The approximate minimum degree algorithm is widely used before numerical factorization to reduce fill-in for sparse matrices. While considerable attention has been given to the numerical factorization process, less focus has been placed on…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-02-26 Yen-Hsiang Chang , Aydın Buluç , James Demmel

This paper presents a novel approach, named the Group Marching Tree (GMT*) algorithm, to planning on GPUs at rates amenable to application within control loops, allowing planning in real-world settings via repeated computation of…

Robotics · Computer Science 2017-05-09 Brian Ichter , Edward Schmerling , Marco Pavone

Edge computing's growing prominence, due to its ability to reduce communication latency and enable real-time processing, is promoting the rise of high-performance, heterogeneous System-on-Chip solutions. While current approaches often…

Artificial Intelligence · Computer Science 2024-09-24 Rakshith Jayanth , Neelesh Gupta , Viktor Prasanna

To train modern large DNN models, pipeline parallelism has recently emerged, which distributes the model across GPUs and enables different devices to process different microbatches in pipeline. Earlier pipeline designs allow multiple…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-08-23 Ziyue Luo , Xiaodong Yi , Guoping Long , Shiqing Fan , Chuan Wu , Jun Yang , Wei Lin

Particle accelerator modeling is an important field of research and development, essential to investigating, designing and operating some of the most complex scientific devices ever built. Kinetic simulations of relativistic, charged…

Accelerator Physics · Physics 2024-05-02 Ryan T. Sandberg , Remi Lehe , Chad E. Mitchell , Marco Garten , Andrew Myers , Ji Qiang , Jean-Luc Vay , Axel Huebl

The vision of super computer at every desk can be realized by powerful and highly parallel CPUs or GPUs or APUs. Graphics processors once specialized for the graphics applications only, are now used for the highly computational intensive…

Distributed, Parallel, and Cluster Computing · Computer Science 2012-04-16 Chittampally Vasanth Raja , Srinivas Balasubramanian , Prakash S Raghavendra

Generative Large Language Models (LLMs) based on the Transformer architecture have recently emerged as a dominant foundation model for a wide range of Natural Language Processing tasks. Nevertheless, their application in real-time scenarios…

Computation and Language · Computer Science 2024-01-04 Coleman Hooper , Sehoon Kim , Hiva Mohammadzadeh , Hasan Genc , Kurt Keutzer , Amir Gholami , Sophia Shao

Sparse Matrix-Matrix Multiplication (SpMM) is a fundamental operation in graph computing and analytics. However, the irregularity of real-world graphs poses significant challenges to achieving efficient SpMM operation for graph data on…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-12-13 Zhonggen Li , Xiangyu Ke , Yifan Zhu , Yunjun Gao , Yaofeng Tu