English
Related papers

Related papers: Regulating Branch Parallelism in LLM Serving

200 papers

With the increasingly giant scales of (causal) large language models (LLMs), the inference efficiency comes as one of the core concerns along the improved performance. In contrast to the memory footprint, the latency bottleneck seems to be…

Computation and Language · Computer Science 2024-04-24 Chen Zhang , Zhuorui Liu , Dawei Song

Large language models (LLMs) are increasingly used for long-content generation (e.g., long Chain-of-Thought reasoning) where decoding efficiency becomes a critical bottleneck: Autoregressive decoding is inherently limited by its sequential…

Computation and Language · Computer Science 2025-06-05 Zhepei Wei , Wei-Lin Chen , Xinyu Zhu , Yu Meng

Transformers have become the dominant architecture for sequence modeling by using self-attention to enable expressive and highly parallel processing. However, the resulting quadratic time and memory costs limit efficiency in long-context…

Machine Learning · Computer Science 2026-05-19 Tristan Gaudreault , Yongyi Mao

Large language models (LLMs) demand significant memory and computation resources. Wafer-scale chips (WSCs) provide high computation power and die-to-die (D2D) bandwidth but face a unique trade-off between on-chip memory and compute…

Hardware Architecture · Computer Science 2025-12-17 Huizheng Wang , Taiquan Wei , Zichuan Wang , Dingcheng Jiang , Qize Yang , Jiaxin Liu , Jingxiang Hou , Chao Li , Jinyi Deng , Yang Hu , Shouyi Yin

Efficiently harnessing GPU compute is critical to improving user experience and reducing operational costs in large language model (LLM) services. However, current inference engine schedulers overlook the attention backend's sensitivity to…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-18 Yitao Yuan , Chenqi Zhao , Bohan Zhao , Zane Cao , Yongchao He , Wenfei Wu

Querying graph data with low latency is an important requirement in application domains such as social networks and knowledge graphs. Graph queries perform multiple hops between vertices. When data is partitioned and stored across multiple…

Databases · Computer Science 2022-12-21 Nathan Ng , Hung Le , Marco Serafini

Efficient parallelization of Large Language Models (LLMs) with long sequences is essential but challenging due to their significant computational and memory demands, particularly stemming from communication bottlenecks in attention…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-12-31 Zongwu Wang , Fangxin Liu , Mingshuai Li , Li Jiang

Speculative decoding (SD), where a draft model provides multiple candidate tokens for the target model to verify in parallel, has demonstrated significant potential for accelerating LLM inference. Yet, existing SD approaches adhere to a…

Machine Learning · Computer Science 2025-09-22 Enyu Zhou , Kai Sheng , Hao Chen , Xin He

In large-scale LLM pre-training systems with 100k+ GPUs, failures become the norm rather than the exception, and restart costs can dominate wall-clock training time. However, existing fault-tolerance mechanisms are largely unprepared for…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-29 Jin Lee , Zhonghao Chen , Xuhang He , Robert Underwood , Bogdan Nicolae , Franck Cappello , Xiaoyi Lu , Sheng Di , Zheng Zhang

When output token counts can be predicted at submission time (Gan et al., 2026), client-side scheduling against a black-box LLM API becomes semi-clairvoyant: decisions condition on coarse token priors even though the provider's internals…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-04-09 Renzhong Yuan , Yijun Zeng , Xiaosong Gao , Linxi Yu , Haochun Liao , Han Wang

Network alignment, or the task of finding corresponding nodes in different networks, is an important problem formulation in many application domains. We propose CAPER, a multilevel alignment framework that Coarsens the input graphs, Aligns…

Social and Information Networks · Computer Science 2022-08-24 Jing Zhu , Danai Koutra , Mark Heimann

Parallel LLM inference scaling involves sampling a set of $N>1$ responses for a single input prompt. However, these $N$ parallel responses tend to be generated independently from each other, partitioning compute resources and leaving…

Artificial Intelligence · Computer Science 2026-02-18 Harry Dong , David Brandfonbrener , Eryk Helenowski , Yun He , Mrinal Kumar , Han Fang , Yuejie Chi , Karthik Abinav Sankararaman

Real-time scheduling and locking protocols are fundamental facilities to construct time-critical systems. For parallel real-time tasks, predictable locking protocols are required when concurrent sub-jobs mutually exclusive access to shared…

Operating Systems · Computer Science 2020-07-03 Maolin Yang , Zewei Chen , Xu Jiang , Nan Guan , Hang Lei

As inference workloads for large language models (LLMs) scale to meet growing user demand, pipeline parallelism (PP) has become a widely adopted strategy for multi-GPU deployment, particularly in cross-node setups, to improve key-value (KV)…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-06-30 Yongchao He , Bohan Zhao , Zheng Cao

With 5G networking, deterministic guarantees are emerging as a key enabler. In this context, we present a scalable Damper-based architecture for Large-scale Deterministic IP Networks (D-LDN) that meets required bounds on end-to-end delay…

Networking and Internet Architecture · Computer Science 2022-09-27 M. Yassine Naghmouchi , Shoushou Ren , Paolo Medagliani , Sébastien Martin , Jérémie Leguay

Auto-regressive decoding in Large Language Models (LLMs) is inherently memory-bound: every generation step requires loading the model weights and intermediate results from memory (e.g., High-Bandwidth Memory (HBM) for GPU servers), making…

Machine Learning · Computer Science 2026-05-13 Yuning Han , Yangchenchen Jin , Dylan Zhao , Jingwei Sun

Long context training is crucial for LLM's context extension. Existing schemes, such as sequence parallelism, incur substantial communication overhead. Pipeline parallelism (PP) reduces this cost, but its effectiveness hinges on…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-04-28 Shiju Wang , Yujie Wang , Ao Sun , Fangcheng Fu , Zijian Zhu , Bin Cui , Xu Han , Kaisheng Ma

In the last decade, an impressive increase in software adaptions has led to a surge in log data production, making manual log analysis impractical and establishing the necessity for automated methods. Conversely, most automated analysis…

Software Engineering · Computer Science 2025-11-19 Shayan Hashemi , Mika Mäntylä

Deploying large language models (LLMs) for online inference is often constrained by limited GPU memory, particularly due to the growing KV cache during auto-regressive decoding. Hybrid GPU-CPU execution has emerged as a promising solution…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-01-16 Jiakun Fan , Yanglin Zhang , Xiangchen Li , Dimitrios S. Nikolopoulos

Modern branch predictors predict the vast majority of conditional branch instructions with near-perfect accuracy, allowing superscalar, out-of-order processors to maximize speculative efficiency and thus performance. However, this…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-10-13 Chit-Kwan Lin , Stephen J. Tarsa