English
Related papers

Related papers: Regulating Branch Parallelism in LLM Serving

200 papers

Speculative decoding accelerates large language model inference by using smaller draft models to generate candidate tokens for parallel verification. However, current approaches are limited by sequential stage dependencies that prevent full…

Artificial Intelligence · Computer Science 2025-05-06 Bradley McDanel , Sai Qian Zhang , Yunhai Hu , Zining Liu

Sequence parallelism (SP) serves as a prevalent strategy to handle long sequences that exceed the memory limit of a single device. However, for linear sequence modeling methods like linear attention, existing SP approaches do not take…

Machine Learning · Computer Science 2025-05-19 Weigao Sun , Zhen Qin , Dong Li , Xuyang Shen , Yu Qiao , Yiran Zhong

Developing an efficient server-based real-time scheduling solution that supports dynamic task-level parallelism is now relevant to even the desktop and embedded domains and no longer only to the high performance computing market niche. This…

Distributed, Parallel, and Cluster Computing · Computer Science 2011-06-15 Luís Nogueira , Luís Miguel Pinho

Efficient large-scale inference of transformer-based large language models (LLMs) remains a fundamental systems challenge, frequently requiring multi-GPU parallelism to meet stringent latency and throughput targets. Conventional tensor…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-02-10 Chong Wang , Nan Du , Tom Gunter , Tao Lei , Kulin Seth , Senyu Tong , Jianyu Wang , Guoli Yin , Xiyou Zhou , Kelvin Zou , Ruoming Pang

This paper summarizes the idea of Subarray-Level Parallelism (SALP) in DRAM, which was published in ISCA 2012, and examines the work's significance and future potential. Modern DRAMs have multiple banks to serve multiple memory requests in…

Hardware Architecture · Computer Science 2018-05-08 Yoongu Kim , Vivek Seshadri , Donghyuk Lee , Jamie Liu , Onur Mutlu

The increasing adoption of large language models (LLMs) necessitates inference serving systems that can deliver both high throughput and low latency. Deploying LLMs with hundreds of billions of parameters on memory-constrained GPUs exposes…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-03-10 Bowen Pang , Kai Li , Feifan Wang

Inference of Large Language Models (LLMs) across computer clusters has become a focal point of research in recent times, with many acceleration techniques taking inspiration from CPU speculative execution. These techniques reduce…

Computation and Language · Computer Science 2024-11-19 Branden Butler , Sixing Yu , Arya Mazaheri , Ali Jannesari

The demand for large language model inference is rapidly increasing. Pipeline parallelism offers a cost-effective deployment strategy for distributed inference but suffers from high service latency. While incorporating speculative decoding…

Machine Learning · Computer Science 2025-09-01 Haofei Yin , Mengbai Xiao , Tinghong Li , Xiao Zhang , Dongxiao Yu , Guanghui Zhang

Actively secure arithmetic MPC is now practical for real applications, but performance and usability are still limited by framework-specific compilation stacks, the need for programmers to explicitly express parallelism, and high…

Cryptography and Security · Computer Science 2025-12-15 Tianye Dai , Hammurabi Mendes , Heuichan Lim

The context window of large language models (LLMs) is rapidly increasing, leading to a huge variance in resource usage between different requests as well as between different phases of the same request. Restricted by static parallelism…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-10-30 Bingyang Wu , Shengyu Liu , Yinmin Zhong , Peng Sun , Xuanzhe Liu , Xin Jin

In LLM inference, the same prompt may yield different outputs across different runs. At the system level, this non-determinism arises from floating-point non-associativity combined with dynamic batching and GPU kernels whose reduction…

Machine Learning · Computer Science 2026-02-02 Raja Gond , Aditya K Kamath , Ramachandran Ramjee , Ashish Panwar

Speculative decoding accelerates LLM inference by drafting a tree of candidate continuations and verifying it in one target forward. Existing drafters fall into two camps with opposite weaknesses. Autoregressive drafters such as EAGLE-3…

Computation and Language · Computer Science 2026-05-22 Weijie Shi , Qiang Xu , Fan Deng , Yaguang Wu , Jiarun Liu , Yehong Xu , Hao Chen , Jia Zhu , Jiajie Xu , Xiangjun Huang , Jian Yang , Xiaofang Zhou

The Integrative Model for Parallelism (IMP) derives a task graph from a higher level description of parallel algorithms. In this note we show how task graph transformations can be used to achieve latency tolerance in the program execution.…

Distributed, Parallel, and Cluster Computing · Computer Science 2018-11-14 Victor Eijkhout

Large Language Models (LLMs) are powerful but often too slow and costly for real-world use during inference. Looped transformers save on parameters by reusing the same weights for multiple computational steps, or "loops." However, this…

Computation and Language · Computer Science 2025-10-30 Bohong Wu , Mengzhao Chen , Xiang Luo , Shen Yan , Qifan Yu , Fan Xia , Tianqi Zhang , Hongrui Zhan , Zheng Zhong , Xun Zhou , Siyuan Qiao , Xingyan Bin

High-throughput inference serving is essential for applications built on large language models (LLMs). Existing serving frameworks reduce request-level and batch-level bubbles through batching and scheduling, but often overlook bubbles…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-25 Fengyao Bai , Hongbin Zhang , Zhitao Chen , Jiangsu Du , Zhiguang Chen , Yutong Lu

Speculative generation has emerged as a promising technique to accelerate inference in large language models (LLMs) by leveraging parallelism to verify multiple draft tokens simultaneously. However, the fundamental limits on the achievable…

Computation and Language · Computer Science 2025-12-15 Sergey Pankratov , Dan Alistarh

Large Transformer networks are increasingly used in settings where low inference latency can improve the end-user experience and enable new applications. However, autoregressive inference is resource intensive and requires parallelism for…

Machine Learning · Computer Science 2024-08-20 Rohan Baskar Prabhakar , Hengrui Zhang , David Wentzlaff

The vast amounts of data used in social, business or traffic networks, biology and other natural sciences are often managed in graph-based data sets, consisting of a few thousand up to billions and trillions of vertices and edges,…

Databases · Computer Science 2021-10-22 Matthias Hauck , Ismail Oukid , Holger Fröning

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

Autoregressive Language Models instantiate a factorized likelihood over token sequences, yet their strictly sequential decoding process imposes an intrinsic lower bound on inference latency. This bottleneck has emerged as a central obstacle…

Computation and Language · Computer Science 2025-09-30 Maxim Divilkovskiy , Vitaly Malygin , Sergey Zlobin , Stanislav Ilyushin , Sultan Isali , Vasily Kalugin , Nuriza Aitassova , Fei Yi , Weidi Zeng