English
Related papers

Related papers: Prefill-Decode Aggregation or Disaggregation? Unif…

200 papers

Large Language Models (LLMs) prompted to generate chain-of-thought (CoT) exhibit impressive reasoning capabilities. Recent attempts at prompt decomposition toward solving complex, multi-step reasoning problems depend on the ability of the…

Computation and Language · Computer Science 2024-02-28 Gurusha Juneja , Subhabrata Dutta , Soumen Chakrabarti , Sunny Manchanda , Tanmoy Chakraborty

Large language model (LLM) decoding is latency-sensitive and often bottlenecked by fragmented operator execution and repeated off-chip materialization of intermediate tensors. Prior work expands fusion scope by leveraging thread-block…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-04-28 ChiHeng Jin , Hongche Yu , Xihui Chen

This paper introduces Helix, a distributed system for high-throughput, low-latency large language model (LLM) serving in heterogeneous GPU clusters. The key idea behind Helix is to formulate inference computation of LLMs over heterogeneous…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-03-07 Yixuan Mei , Yonghao Zhuang , Xupeng Miao , Juncheng Yang , Zhihao Jia , Rashmi Vinayak

Large Language Models (LLMs) have demonstrated impressive performance on multiple-choice question answering (MCQA) benchmarks, yet they remain highly vulnerable to minor input perturbations. In this paper, we introduce and evaluate Token…

Computation and Language · Computer Science 2025-06-12 Jui-Ming Yao , Hao-Yuan Chen , Zi-Xian Tang , Bing-Jia Tan , Sheng-Wei Peng , Bing-Cheng Xie , Shun-Feng Su

The increasing demand for Large Language Models (LLMs) across various applications has led to a significant shift in the design of deep learning serving systems. Deploying LLMs, particularly in multi-tenant environments, poses substantial…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-09-25 Bodun Hu , Jiamin Li , Le Xu , Myungjin Lee , Akshay Jajoo , Geon-Woo Kim , Hong Xu , Aditya Akella

We propose a straightforward approach called Distillation Contrastive Decoding (DCD) to enhance the reasoning capabilities of Large Language Models (LLMs) during inference. In contrast to previous approaches that relied on smaller amateur…

Computation and Language · Computer Science 2024-08-26 Phuc Phan , Hieu Tran , Long Phan

Post-training quantization (PTQ) is an effective technique for compressing large language models (LLMs). However, while uniform-precision quantization is computationally efficient, it often compromises model performance. To address this, we…

Machine Learning · Computer Science 2025-05-27 Wei Huang , Haotong Qin , Yangdong Liu , Yawei Li , Qinshuo Liu , Xianglong Liu , Luca Benini , Michele Magno , Shiming Zhang , Xiaojuan Qi

The generation speed of LLMs are bottlenecked by autoregressive decoding, where tokens are predicted sequentially one by one. Alternatively, diffusion large language models (dLLMs) theoretically allow for parallel token generation, but in…

Computation and Language · Computer Science 2025-11-03 Daniel Israel , Guy Van den Broeck , Aditya Grover

Attention mechanisms underpin the success of large language models (LLMs), yet their substantial computational and memory overhead poses challenges for optimizing efficiency and performance. A critical bottleneck arises as KV cache and…

Computation and Language · Computer Science 2025-07-24 Luoyang Sun , Cheng Deng , Jiwen Jiang , Xinjian Wu , Haifeng Zhang , Lei Chen , Lionel Ni , Jun Wang

Conventional continual pretraining (CPT) for large language model (LLM) domain adaptation often suffers from catastrophic forgetting and limited domain capacity. Existing strategies adopt layer expansion, introducing additional trainable…

Machine Learning · Computer Science 2025-10-14 Jinyang Zhang , Yue Fang , Hongxin Ding , Weibin Liao , Muyang Ye , Xu Chu , Junfeng Zhao , Yasha Wang

This paper introduces a simple and scalable approach to improve the data efficiency of large language model (LLM) training by augmenting existing text data with thinking trajectories. The compute for pre-training LLMs has been growing at an…

Computation and Language · Computer Science 2025-10-20 Liang Wang , Nan Yang , Shaohan Huang , Li Dong , Furu Wei

The rapid rise of large language models (LLMs) in text streaming services has introduced significant cost and Quality of Experience (QoE) challenges in serving millions of daily requests, especially in meeting Time-To-First-Token (TTFT) and…

Machine Learning · Computer Science 2025-05-27 Ting Sun , Penghan Wang , Fan Lai

Large language models (LLMs) are increasingly deployed on customer devices. To support them, current devices are adopting SoCs (System on Chip) with NPUs (Neural Processing Unit) installed. Although high performance is expected, LLM…

Hardware Architecture · Computer Science 2025-11-17 Jianyu Wei , Qingtao Li , Shijie Cao , Lingxiao Ma , Zixu Hao , Yanyong Zhang , Xiaoyan Hu , Ting Cao

Large language models (LLMs) exhibit exceptional performance across a wide range of tasks; however, their token-by-token autoregressive generation process significantly hinders inference speed. Speculative decoding presents a promising…

Computation and Language · Computer Science 2025-03-04 Kai Lv , Honglin Guo , Qipeng Guo , Xipeng Qiu

LoRA enables efficient customization of LLMs and is widely used in multi-tenant and multi-task serving. However, emerging model architectures such as MoE significantly increase LoRA memory cost, making existing coupled LoRA serving designs…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-04-09 Hongyu Chen , Letian Ruan , Zilin Xu , Yuchen Li , Xinyu Chen , Jingwen Leng , Bingsheng He , Minyi Guo , Shixuan Sun

The integration of Artificial Intelligence (AI) in healthcare presents a transformative potential for enhancing operational efficiency and health outcomes. Large Language Models (LLMs), such as ChatGPT, have shown their capabilities in…

Computation and Language · Computer Science 2024-05-03 Dou Liu , Ying Han , Xiandi Wang , Xiaomei Tan , Di Liu , Guangwu Qian , Kang Li , Dan Pu , Rong Yin

This paper presents "Predictive Pipelined Decoding (PPD)," an approach that speeds up greedy decoding in Large Language Models (LLMs) while maintaining the exact same output as the original decoding. Unlike conventional strategies, PPD…

Computation and Language · Computer Science 2024-07-30 Seongjun Yang , Gibbeum Lee , Jaewoong Cho , Dimitris Papailiopoulos , Kangwook Lee

This research introduces a transformative framework for integrating Vision-Enhanced Large Language Models (LLMs) with advanced transformer-based architectures to tackle challenges in high-resolution image synthesis and multimodal data…

Computer Vision and Pattern Recognition · Computer Science 2026-01-06 Karthikeya KV

Deep learning (DL) jobs use multi-dimensional parallelism, i.e. combining data, model, and pipeline parallelism, to use large GPU clusters efficiently. Long-running jobs may experience changes to their GPU allocation: (i) resource…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-09-27 Marcel Wagenländer , Guo Li , Bo Zhao , Luo Mai , Peter Pietzuch

Existing alignment techniques for Large Language Models (LLMs), such as Direct Preference Optimization (DPO), typically treat the model as a monolithic entity, applying uniform optimization pressure across all layers. This approach…

Computation and Language · Computer Science 2025-10-15 Yukun Zhang , Qi Dong