English
Related papers

Related papers: Regulating Branch Parallelism in LLM Serving

200 papers

We present an algorithm for controlling and scheduling multiple linear time-invariant processes on a shared bandwidth limited communication network using adaptive sampling intervals. The controller is centralized and computes at every…

Systems and Control · Computer Science 2015-06-25 Erik Henriksson , Daniel E. Quevedo , Edwin G. W. Peters , Henrik Sandberg , Karl Henrik Johansson

We present a parallel GPU-accelerated solver for branch Model Predictive Control problems. Based on iterative LQR methods, our solver exploits the tree-sparse structure and implements temporal parallelism using the parallel scan algorithm.…

Systems and Control · Electrical Eng. & Systems 2025-06-17 Luyao Zhang , Chenghuai Lin , Sergio Grammatico

The increasing adoption of heterogeneous platforms that combine CPUs with accelerators such as GPUs in high-performance computing (HPC) introduces new challenges for performance analysis and optimization. Traditional efficiency metrics,…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-03-30 Ghazal Rahimi , Victor Lopez , Marc Clascà , Joan Vinyals Ylla Català , Jesus Labarta , Marta Garcia-Gasulla

The evolution of Large Language Model (LLM) serving towards complex, distributed architectures--specifically the P/D-separated, large-scale DP+EP paradigm--introduces distinct scheduling challenges. Unlike traditional deployments where…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-19 Jian Tian , Shuailong Li , Yang Cao , Wenbo Cui , Minghan Zhu , Wenkang Wu , Jianming Zhang , Yanpeng Wang , Zhiwen Xiao , Zhenyu Hou , Dou Shen

We present tensor and sequence parallelism (TSP), a parallel execution strategy that folds tensor parallelism and sequence parallelism onto a single device axis. In conventional multi-dimensional parallelism layouts, tensor parallelism (TP)…

Computation and Language · Computer Science 2026-04-30 Vasu Shyam , Anna Golubeva , Quentin Anthony

The advent of efficient interior point optimization methods has enabled the tractable solution of large-scale linear and nonlinear programming (NLP) problems. A prominent example of such a method is seen in Ipopt, a widely-used, open-source…

Optimization and Control · Mathematics 2019-09-19 Byron Tasseff , Carleton Coffrin , Andreas Wächter , Carl Laird

Multimodal large language models (MLLMs) extend LLMs to handle images, videos, and audio by incorporating feature extractors and projection modules. However, these additional components -- combined with complex inference pipelines and…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-12 Zedong Liu , Shenggan Cheng , Guangming Tan , Yang You , Dingwen Tao

Large language models (LLMs) have achieved impressive results on multi-step mathematical reasoning, yet at the cost of high computational overhead. This challenge is particularly acute for test-time scaling methods such as parallel…

Machine Learning · Computer Science 2026-03-24 Yuanlin Chu , Bo Wang , Xiang Liu , Hong Chen , Aiwei Liu , Xuming Hu

Graphics Processing Units (GPUs) excel at regular data-parallel workloads where massive hardware parallelism can be readily exploited. In contrast, many important irregular applications are naturally expressed as task parallelism with a…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-04-08 Yuki Maeda , Kenjiro Taura

Modern multicore system-on-chips (SoCs) share off-chip DRAM across cores, where bank-level interference can significantly degrade performance and threaten real-time guarantees. While prior work has focused on per-core bandwidth regulation,…

Hardware Architecture · Computer Science 2026-03-30 Connor Rudy Sullivan , Amin Mamandipoor , Cole Ridge Strickler , Heechul Yun

In the FPGA (Field Programmable Gate Arrays) design flow, one of the most time-consuming step is the routing of nets. Therefore, there is a need to accelerate it. In a recent paper by Hoo et. al., the authors have developed a Linear…

Distributed, Parallel, and Cluster Computing · Computer Science 2018-08-21 Rohit Agrawal , Chin Hao Hoo , Kapil Ahuja , Akash Kumar

To meet the evolving data rate requirements of emerging wireless communication technologies, many parallel architectures have been proposed to implement high throughput turbo decoders. However, concurrent memory reading/writing in parallel…

Information Theory · Computer Science 2014-03-27 Guohui Wang , Hao Shen , Yang Sun , Joseph R. Cavallaro , Aida Vosoughi , Yuanbin Guo

We introduce the fastest known exact algorithm~for~the multiterminal cut problem with k terminals. In particular, we engineer existing as well as new data reduction rules. We use the rules within a branch-and-reduce framework and to boost…

Data Structures and Algorithms · Computer Science 2019-08-20 Monika Henzinger , Alexander Noe , Christian Schulz

Large language models (LLMs) iteratively generate text token by token, with memory usage increasing with the length of generated token sequences. Since the request generation length is generally unpredictable, it is difficult to estimate…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-03-11 Ke Cheng , Wen Hu , Zhi Wang , Hongen Peng , Jianguo Li , Sheng Zhang

Extending the context length (i.e., the maximum supported sequence length) of LLMs is of paramount significance. To facilitate long context training of LLMs, sequence parallelism has emerged as an essential technique, which scatters each…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-02-12 Yujie Wang , Shiju Wang , Shenhan Zhu , Fangcheng Fu , Xinyi Liu , Xuefeng Xiao , Huixia Li , Jiashi Li , Faming Wu , Bin Cui

Large language model (LLM) applications are blindfolded to the infrastructure underneath and generate tokens autoregressively, indifferent to the system load, thus risking inferencing latency inflation and poor user experience. Our…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-10-20 Tella Rajashekhar Reddy , Atharva Deshmukh , Karan Tandon , Rohan Gandhi , Anjaly Parayil , Debopam Bhattacherjee

While blockchains initially gained popularity in the realm of cryptocurrencies, their widespread adoption is expanding beyond conventional applications, driven by the imperative need for enhanced data security. Despite providing a secure…

Cryptography and Security · Computer Science 2024-12-10 Faisal Haque Bappy , Tarannum Shaila Zaman , Md Sajidul Islam Sajid , Mir Mehedi Ahsan Pritom , Tariqul Islam

This work introduces TapirXLA, a replacement for TensorFlow's XLA compiler that embeds recursive fork-join parallelism into XLA's low-level representation of code. Machine-learning applications rely on efficient parallel processing to…

Performance · Computer Science 2021-09-08 Tao B. Schardl , Siddharth Samsi

The definition of a Neural Network architecture is one of the most critical and challenging tasks to perform. In this paper, we propose ParallelMLPs. ParallelMLPs is a procedure to enable the training of several independent Multilayer…

Machine Learning · Computer Science 2022-06-20 Felipe Costa Farias , Teresa Bernarda Ludermir , Carmelo Jose Albanez Bastos-Filho

Speculative decoding accelerates LLM inference by using a fast draft model to generate tokens and a more accurate target model to verify them. Its performance depends on the $\textit{acceptance length}$, or number of draft tokens accepted…

Computation and Language · Computer Science 2026-05-20 Avinash Kumar , Sujay Sanghavi , Poulami Das