English
Related papers

Related papers: Tree Attention: Topology-aware Decoding for Long-C…

200 papers

Decision trees are essential yet NP-complete to train, prompting the widespread use of heuristic methods such as CART, which suffers from sub-optimal performance due to its greedy nature. Recently, breakthroughs in finding optimal decision…

Machine Learning · Computer Science 2023-11-14 Jiayang Ren , Valentín Osuna-Enciso , Morimasa Okamoto , Qiangqiang Mao , Chaojie Ji , Liang Cao , Kaixun Hua , Yankai Cao

We present context parallelism for long-context large language model inference, which achieves near-linear scaling for long-context prefill latency with up to 128 H100 GPUs across 16 nodes. Particularly, our method achieves 1M context…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-04-22 Amy Yang , Jingyi Yang , Aya Ibrahim , Xinfeng Xie , Bangsheng Tang , Grigory Sizov , Jeremy Reizenstein , Jongsoo Park , Jianyu Huang

A concurrent binary tree (CBT) is a GPU-friendly data-structure suitable for the generation of bisection based terrain tessellations, i.e., adaptive triangulations over square domains. In this paper, we expand the benefits of this…

Graphics · Computer Science 2024-07-03 Anis Benyoub , Jonathan Dupuy

Large language model (LLM) serving is fundamentally limited by inefficient hardware utilization. Autoregressive (AR) decoding underutilizes GPUs due to its strictly sequential execution, while diffusion LLMs (DLLMs) improve throughput by…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-26 Chiyue Wei , Cong Guo , Bowen Duan , Junyao Zhang , Haoxuan Shan , Yifei Wang , Yangjie Zhou , Hai "Helen" Li , Danyang Zhuo , Yiran Chen

Transformer is a powerful architecture that achieves superior performance on various sequence learning tasks, including neural machine translation, language understanding, and sequence prediction. At the core of the Transformer is the…

Machine Learning · Computer Science 2019-11-13 Yao-Hung Hubert Tsai , Shaojie Bai , Makoto Yamada , Louis-Philippe Morency , Ruslan Salakhutdinov

Autoregressive (AR) encoder-decoder neural networks have proved successful in many NLP problems, including Semantic Parsing -- a task that translates natural language to machine-readable parse trees. However, the sequential prediction…

Computation and Language · Computer Science 2023-03-31 Sid Wang , Akshat Shrivastava , Sasha Livshits

Processing long-context inputs with large language models presents a significant challenge due to the enormous memory requirements of the Key-Value (KV) cache during inference. Existing KV cache compression methods exhibit noticeable…

Computation and Language · Computer Science 2025-07-29 Dongquan Yang , Yifan Yang , Xiaotian Yu , Xianbiao Qi , Rong Xiao

Multi-scale deformable attention (MSDeformAttn) has emerged as a key mechanism in various vision tasks, demonstrating explicit superiority attributed to multi-scale grid-sampling. However, this newly introduced operator incurs irregular…

Hardware Architecture · Computer Science 2024-03-19 Yansong Xu , Dongxu Lyu , Zhenyu Li , Zilong Wang , Yuzhou Chen , Gang Wang , Zhican Wang , Haomin Li , Guanghui He

Cost of serving large language models (LLM) is high, but the expensive and scarce GPUs are poorly efficient when generating tokens sequentially, unless the batch of sequences is enlarged. However, the batch size is limited by some…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-03-19 Jiaao He , Jidong Zhai

Prefix-sharing among multiple prompts presents opportunities to combine the operations of the shared prefix, while attention computation in the decode stage, which becomes a critical bottleneck with increasing context lengths, is a…

To mitigate the computational complexity in the self-attention mechanism on long sequences, linear attention utilizes computation tricks to achieve linear complexity, while state space models (SSMs) popularize a favorable practice of using…

Machine Learning · Computer Science 2024-06-17 Zicheng Liu , Siyuan Li , Li Wang , Zedong Wang , Yunfan Liu , Stan Z. Li

Pre-training Transformer from large-scale raw texts and fine-tuning on the desired task have achieved state-of-the-art results on diverse NLP tasks. However, it is unclear what the learned attention captures. The attention computed by…

Computation and Language · Computer Science 2019-11-05 Yau-Shian Wang , Hung-Yi Lee , Yun-Nung Chen

Designing a unified neural network to efficiently and inherently process sequential data with arbitrary lengths is a central and challenging problem in sequence modeling. The design choices in Transformer, including quadratic complexity and…

Optimizing deep learning algorithms currently requires slow, manual derivation, potentially leaving much performance untapped. Methods like FlashAttention have achieved a x6 performance improvement over native PyTorch by avoiding…

Machine Learning · Computer Science 2025-01-22 Vincent Abbott , Gioele Zardini

The connection between dependency trees and spanning trees is exploited by the NLP community to train and to decode graph-based dependency parsers. However, the NLP literature has missed an important difference between the two structures:…

Computation and Language · Computer Science 2020-10-08 Ran Zmigrod , Tim Vieira , Ryan Cotterell

As the length of input text increases, the key-value (KV) cache in LLMs imposes prohibitive GPU memory costs and limits long-context inference on resource constrained devices. Existing approaches, such as KV quantization and pruning, reduce…

Machine Learning · Computer Science 2025-12-24 Tenghui Li , Guoxu Zhou , Xuyang Zhao , Yuning Qiu , Qibin Zhao

Stack Long Short-Term Memory (StackLSTM) is useful for various applications such as parsing and string-to-tree neural machine translation, but it is also known to be notoriously difficult to parallelize for GPU training due to the fact that…

Computation and Language · Computer Science 2019-04-09 Shuoyang Ding , Philipp Koehn

Cross-attention is commonly adopted in multimodal large language models (MLLMs) for integrating visual information into the language backbone. However, in applications with large visual inputs, such as video understanding, processing a…

Computer Vision and Pattern Recognition · Computer Science 2025-05-29 Tzu-Tao Chang , Shivaram Venkataraman

In long-context large language model (LLM) inference, the prefill stage dominates computation due to self-attention over the complete input context. Sparse attention significantly reduces self-attention computation by limiting each token's…

Hardware Architecture · Computer Science 2026-02-25 Rakshith Jayanth , Viktor Prasanna

With the increasing volumes of Large Language Models (LLMs) and the expanding context lengths, attention computation has become a key performance bottleneck in LLM serving. For fast attention computation, recent practices often parallelize…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-03-12 Di Liu , Yifei Liu , Chen Chen , Zhibin Yu , Xiaoyi Fan , Quan Chen , Minyi Guo