paper-with-me

Papers

APB: Accelerating Distributed Long-Context Inference by Passing Compressed Context Blocks across GPUs

2025-02-17 · Yuxiang Huang, Mingye Li, Xu Han, Chaojun Xiao, Weilin Zhao, Sun Ao, Hao Zhou, Jie zhou, Zhiyuan Liu, Maosong Sun

While long-context inference is crucial for advancing large language model (LLM) applications, its prefill speed remains a significant bottleneck. Current approaches, including sequence parallelism strategies and compute reduction through approximate attention mechanisms, still fall short of delivering optimal inference efficiency. This hinders scaling the inputs to longer sequences and processing long-context queries in a timely manner. To address this, we introduce APB, an efficient long-context inference framework that leverages multi-host approximate attention to enhance prefill speed by reducing compute and enhancing parallelism simultaneously. APB introduces a communication mechanism for essential key-value pairs within a sequence parallelism framework, enabling a faster inference speed while maintaining task performance. We implement APB by incorporating a tailored FlashAttn kernel alongside optimized distribution strategies, supporting diverse models and parallelism configurations. APB achieves speedups of up to 9.2x, 4.2x, and 1.6x compared with FlashAttn, RingAttn, and StarAttn, respectively, without any observable task performance degradation. We provide the implementation and experiment code of APB in https://github.com/thunlp/APB.

📄 PDF Abstract BibTeX arXiv:2502.12085

Code (1)

thunlp/apb 공식 구현

Tasks

Language ModelingLanguage ModellingLarge Language Model

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

LycheeDecode: Accelerating Long-Context LLM Inference via Hybrid-Head Sparse Decoding

2026-02-04 · Gang Lin, Dongfang Li, Zhuoen Chen, Yukun Shi 외 arxiv

The proliferation of long-context large language models (LLMs) exposes a key bottleneck: the rapidly expanding key-value cache during decoding, which imposes heavy memory and latency costs. While recent approaches attemp…

Long-Context Understanding

SlimInfer: Accelerating Long-Context LLM Inference via Dynamic Token Pruning

2025-08-08 · Lingkun Long, Rubing Yang, Yushi Huang, Desheng Hui 외 arxiv

Long-context inference for Large Language Models (LLMs) is heavily limited by high computational demands. While several existing methods optimize attention computation, they still process the full set of hidden states at…

AdaSkip: Adaptive Sublayer Skipping for Accelerating Long-Context LLM Inference

2025-01-04 · Zhuomin He, Yizhen Yao, Pengfei Zuo, Bin Gao 외

Long-context large language models (LLMs) inference is increasingly critical, motivating a number of studies devoted to alleviating the substantial storage and computational costs in such scenarios. Layer-wise skipping m…

TawPipe: Topology-Aware Weight Pipeline Parallelism for Accelerating Long-Context Large Models Training

2025-11-12 · Houming Wu, Ling Chen arxiv

Training large language models (LLMs) is fundamentally constrained by limited device memory and costly inter-device communication. Although pipeline parallelism alleviates memory pressure by partitioning models across de…

Mustafar: Promoting Unstructured Sparsity for KV Cache Pruning in LLM Inference

2025-05-28 · Donghyeon Joo, Helya Hosseini, Ramyad Hadidi, Bahar Asgari

We demonstrate that unstructured sparsity significantly improves KV cache compression for LLMs, enabling sparsity levels up to 70% without compromising accuracy or requiring fine-tuning. We conduct a systematic explorati…