paper-with-me

Papers

Communication Compression for Tensor Parallel LLM Inference

2024-11-14 · Jan Hansen-Palmus, Michael Truong Le, Oliver Hausdörfer, Alok Verma

Large Language Models (LLMs) have pushed the frontier of artificial intelligence but are comprised of hundreds of billions of parameters and operations. For faster inference latency, LLMs are deployed on multiple hardware accelerators through various Model Parallelism strategies. Our paper looks into the details on one such strategy - Tensor Parallel - and proposes to reduce latency by compressing inter-accelerator communication. We leverage fine grained quantization techniques to compress selected activations by 3.5 - 4.5x. Our proposed method leads up to 2x reduction of time-to-first-token (TTFT) with negligible model performance degradation.

📄 PDF Abstract BibTeX arXiv:2411.09510

Code (0)

등록된 구현이 없습니다.

Tasks

Quantization

Similar Papers 제목 키워드 기반

TACO: Efficient Communication Compression of Intermediate Tensors for Scalable Tensor-Parallel LLM Training

2026-04-27 · Man Liu, Xingchen Liu, Xingjian Tian, Bing Lu 외 arxiv

Handling communication overhead in large-scale tensor-parallel training remains a critical challenge due to the dense, near-zero distributions of intermediate tensors, which exacerbate errors under frequent communication…

Flash Communication: Reducing Tensor Parallelization Bottleneck for Fast Large Language Model Inference

2024-12-06 · Qingyuan Li, Bo Zhang, Liang Ye, Yifan Zhang 외

The ever-increasing sizes of large language models necessitate distributed solutions for fast inference that exploit multi-dimensional parallelism, where computational loads are split across various accelerators such as …

GPULanguage ModelingLanguage ModellingLarge Language Model

VcLLM: Video Codecs are Secretly Tensor Codecs

2024-06-29 · Ceyu Xu, Yongji Wu, Xinyu Yang, Beidi Chen 외

As the parameter size of large language models (LLMs) continues to expand, the need for a large memory footprint and high communication bandwidth have become significant bottlenecks for the training and inference of LLMs…

SPD: Sync-Point Drop for Efficient Tensor Parallelism of Large Language Models

2025-02-28 · Han-Byul Kim, Duc Hoang, Arnav Kundu, Mohammad Samragh 외

With the rapid expansion in the scale of large language models (LLMs), enabling efficient distributed inference across multiple computing units has become increasingly critical. However, communication overheads from popu…

Towards Low-bit Communication for Tensor Parallel LLM Inference

2024-11-12 · Harry Dong, Tyler Johnson, Minsik Cho, Emad Soroush

Tensor parallelism provides an effective way to increase server large language model (LLM) inference efficiency despite adding an additional communication cost. However, as server LLMs continue to scale in size, they wil…

Language ModelingLanguage ModellingLarge Language ModelQuantization