English
Related papers

Related papers: Regulating Branch Parallelism in LLM Serving

200 papers

The transition from standard generative AI to \emph{reasoning-centric architectures}, exemplified by models capable of extensive Chain-of-Thought~(CoT) processing, marks a fundamental paradigm shift in system requirements. Unlike…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-20 Moiz Arif , Avinash Maurya , Sudharshan Vazhkudai , Bogdan Nicolae

Low-latency decoding for large language models (LLMs) is crucial for applications like chatbots and code assistants, yet generating long outputs remains slow in single-query settings. Prior work on speculative decoding (which combines a…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-06-16 Ziyi Zhang , Ziheng Jiang , Chengquan Jiang , Menghan Yu , Size Zheng , Haibin Lin , Henry Hoffmann , Xin Liu

Large Language Model (LLM) inference services demand exceptionally high availability and low latency, yet multi-GPU Tensor Parallelism (TP) makes them vulnerable to single-GPU failures. We present AnchorTP, a state-preserving elastic TP…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-18 Wendong Xu , Chujie Chen , He Xiao , Kuan Li , Jing Xiong , Chen Zhang , Wenyong Zhou , Chaofan Tao , Yang Bai , Bei Yu , Ngai Wong

Diffusion Large Language Models (dLLMs) have demonstrated significant potential for high-speed inference. However, current confidence-driven decoding strategies are constrained by limited parallelism, typically achieving only 1--3 tokens…

Computation and Language · Computer Science 2025-12-23 Chenkai Xu , Yijie Jin , Jiajun Li , Yi Tu , Guoping Long , Dandan Tu , Mingcong Song , Hongjie Si , Tianqi Hou , Junchi Yan , Zhijie Deng

LLM training is scaled up to 10Ks of GPUs by a mix of data-(DP) and model-parallel (MP) execution. Critical to achieving efficiency is tensor-parallel (TP; a form of MP) execution within tightly-coupled subsets of GPUs, referred to as a…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-04-09 Daiyaan Arfeen , Dheevatsa Mudigere , Ankit More , Bhargava Gopireddy , Ahmet Inci , Gregory R. Ganger

In the realm of Large Language Model (LLM) inference, the inherent structure of transformer models coupled with the multi-GPU tensor parallelism strategy leads to a sequential execution of computation and communication. This results in…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-09-18 Bin Xiao , Lei Su

As large language models (LLMs) have shown great success in many tasks, they are used in various applications. While a lot of works have focused on the efficiency of single-LLM application (e.g., offloading, request scheduling, parallelism…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-03-24 Jingzhi Fang , Yanyan Shen , Yue Wang , Lei Chen

Decoding in a Transformer based language model is inherently sequential as a token's embedding needs to pass through all the layers in the network before the generation of the next token can begin. In this work, we propose a new…

Machine Learning · Computer Science 2025-08-27 Dylan Cutler , Arun Kandoor , Nishanth Dikkala , Nikunj Saunshi , Xin Wang , Rina Panigrahy

Parallel programming models can encourage performance portability by moving the responsibility for work assignment and data distribution from the programmer to a runtime system. However, analyzing the resulting implicit memory allocations,…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-03-14 Fabian Knorr , Philip Salzmann , Peter Thoman , Thomas Fahringer

Applications running in modern multithreaded environments are sometimes \emph{over-threaded}. The excess threads do not improve performance, and in fact may act to degrade performance via \emph{scalability collapse}. Often, such software…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-06-13 Dave Dice

Diffusion Language Models (dLLMs) have garnered significant attention for their potential in highly parallel processing. The parallel capabilities of existing dLLMs stem from the assumption of conditional independence at high confidence…

Machine Learning · Computer Science 2026-05-13 Haohui Zhang , Zhiye Wang , Xiaoying Gan , Xinbing Wang , Bo Jiang

As large language models (LLMs) grow in popularity for their diverse capabilities, improving the efficiency of their inference systems has become increasingly critical. Batching LLM requests is a critical step in scheduling the inference…

Computation and Language · Computer Science 2024-12-09 Ozgur Guldogan , Jackson Kunde , Kangwook Lee , Ramtin Pedarsani

Neural networks achieve strong empirical performance, but robustness concerns still hinder deployment in safety-critical applications. Formal verification provides robustness guarantees, but current methods face a scalability-completeness…

Machine Learning · Computer Science 2026-02-06 Wenting Li , Saif R. Kazi , Russell Bent , Duo Zhou , Huan Zhang

Static-graph LLM decoders provide predictable launches, fixed tensor shapes, and low submission overhead, but online decoding exposes highly irregular KV-cache behavior: request lengths differ, EOS events arrive asynchronously, and logical…

Hardware Architecture · Computer Science 2026-05-12 Zhiqing Zhong , Zhijing Ye , Jian Zhang , Weijian Zheng , Bolun Sun , Xiaodong Yu

Speculative decoding accelerates LLM inference by utilizing otherwise idle computational resources during memory-to-chip data transfer. Current speculative decoding methods typically assume a considerable amount of available computing…

Computation and Language · Computer Science 2025-11-26 Luohe Shi , Zuchao Li , Lefei Zhang , Baoyuan Qi , Guoming Liu , Hai Zhao

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

As LLMs scale to multi-million-token KV histories, real-time autoregressive decoding under tight Token-to-Token Latency (TTL) constraints faces growing pressure. Two core bottlenecks dominate: accessing Feed-Forward Network (FFN) weights…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-07-11 Nidhi Bhatia , Ankit More , Ritika Borkar , Tiyasa Mitra , Ramon Matas , Ritchie Zhao , Maximilian Golub , Dheevatsa Mudigere , Brian Pharris , Bita Darvish Rouhani

To achieve high performance on modern computers, it is vital to map algorithmic parallelism to that inherent in the hardware. From an application developer's perspective, it is also important that code can be maintained in a portable manner…

Distributed, Parallel, and Cluster Computing · Computer Science 2016-06-20 Alan Gray , Kevin Stratford

We present a framework in which a large language model (LLM) acts as an online adaptive controller for SIMP topology optimization, replacing conventional fixed-schedule continuation with real-time, state-conditioned parameter decisions. At…

Computational Engineering, Finance, and Science · Computer Science 2026-05-18 Shaoliang Yang , Jun Wang , Yunsheng Wang

Tree-based demappers for multiple-input multiple-output (MIMO) detection such as the sphere decoder can achieve near-optimal performance but incur high computational cost due to their sequential nature. In this paper, we propose the…

Information Theory · Computer Science 2022-09-12 Daniel E. Worrall , Markus Peschl , Arash Behboodi , Roberto Bondesan