English
Related papers

Related papers: TP-Aware Dequantization

200 papers

This paper presents a modular approach to accelerate inference in large language models (LLMs) by adding early exit heads at intermediate transformer layers. Each head is trained in a self-supervised manner to mimic the main model's…

Computation and Language · Computer Science 2026-02-13 Florian Valade

We present LayerSkip, an end-to-end solution to speed-up inference of large language models (LLMs). First, during training we apply layer dropout, with low dropout rates for earlier layers and higher dropout rates for later layers, and an…

Large Language Model (LLM) inference uses an autoregressive manner to generate one token at a time, which exhibits notably lower operational intensity compared to earlier Machine Learning (ML) models such as encoder-only transformers and…

Hardware Architecture · Computer Science 2025-05-06 Yufeng Gu , Alireza Khadem , Sumanth Umesh , Ning Liang , Xavier Servot , Onur Mutlu , Ravi Iyer , Reetuparna Das

One limitation of existing Transformer-based models is that they cannot handle very long sequences as input since their self-attention operations exhibit quadratic time and space complexity. This problem becomes especially acute when…

Machine Learning · Computer Science 2024-05-07 Yuzhen Mao , Martin Ester , Ke Li

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…

Machine Learning · Computer Science 2025-05-27 Yuxiang Huang , Mingye Li , Xu Han , Chaojun Xiao , Weilin Zhao , Sun Ao , Hao Zhou , Jie Zhou , Zhiyuan Liu , Maosong Sun

Diffusion large language models (dLLMs) represent a significant advancement in text generation, offering parallel token decoding capabilities. However, existing open-source implementations suffer from quality-speed trade-offs that impede…

Computation and Language · Computer Science 2025-10-09 Fanheng Kong , Jingyuan Zhang , Yahui Liu , Zirui Wu , Yu Tian , Victoria W. , Guorui Zhou

Large Language Models (LLMs) encounter severe memory inefficiencies during long-context inference due to conventional handling of key-value (KV) caches. In this work, we introduce a novel integration of PagedAttention with PyTorch's…

Machine Learning · Computer Science 2025-06-10 Thomas Joshi , Herman Saini , Neil Dhillon , Antoni Viros i Martin , Kaoutar El Maghraoui

How can we effectively handle queries for on-device large language models (LLMs) with varying runtime constraints, such as latency and accuracy? Multi-scale quantization addresses this challenge by enabling memory-efficient runtime model…

Machine Learning · Computer Science 2025-12-09 Sangwoo Kwon , Seong Hoon Seo , Jae W. Lee , Yeonhong Park

Large Language Models (LLMs) have been extensively researched and used in both academia and industry since the rise in popularity of the Transformer model, which demonstrates excellent performance in AI. However, the computational demands…

Machine Learning · Computer Science 2024-11-06 Jiedong Lang , Zhehao Guo , Shuyu Huang

Deploying Large Language Models (LLMs) locally on mobile devices presents a significant challenge due to their extensive memory requirements. In this paper, we introduce LinguaLinked, a system for decentralized, distributed LLM inference on…

Machine Learning · Computer Science 2023-12-04 Junchen Zhao , Yurun Song , Simeng Liu , Ian G. Harris , Sangeetha Abdu Jyothi

This paper presents a comprehensive analysis of quantization techniques for optimizing Large Language Models (LLMs), specifically focusing on Post-Training Quantization (PTQ) and Quantization-Aware Training (QAT). Through empirical…

Machine Learning · Computer Science 2024-11-12 Jahid Hasan

Large Language Models are growing in size, and we expect them to continue to do so, as larger models train quicker. However, this increase in size will severely impact inference costs. Therefore model compression is important, to retain the…

Machine Learning · Computer Science 2024-04-10 Georgy Tyukin

Adjusting the latency, power, and accuracy of natural language understanding models is a desirable objective of an efficient architecture. This paper proposes an efficient Transformer architecture that adjusts the inference computational…

Computation and Language · Computer Science 2024-09-20 Sajjad Kachuee , Mohammad Sharifkhani

Large Language Models (LLMs) are trained to support an increasing number of languages, yet their predefined tokenizers remain a bottleneck for adapting models to lower-resource or distinct-script languages. Existing tokenizer transfer…

Computation and Language · Computer Science 2026-05-12 Mykola Haltiuk , Aleksander Smywinski-Pohl

Quantization has established itself as the primary approach for decreasing the computational and storage expenses associated with Large Language Models (LLMs) inference. The majority of current research emphasizes quantizing weights and…

Machine Learning · Computer Science 2024-10-07 Moran Shkolnik , Maxim Fishman , Brian Chmiel , Hilla Ben-Yaacov , Ron Banner , Kfir Yehuda Levy

Recent advancements in large language models (LLMs) boasting billions of parameters have generated a significant demand for efficient deployment in inference workloads. The majority of existing approaches rely on temporal architectures that…

Machine Learning · Computer Science 2024-04-09 Hongzheng Chen , Jiahao Zhang , Yixiao Du , Shaojie Xiang , Zichao Yue , Niansong Zhang , Yaohui Cai , Zhiru Zhang

Ternary quantization has emerged as a powerful technique for reducing both computational and memory footprint of large language models (LLM), enabling efficient real-time inference deployment without significantly compromising model…

Hardware Architecture · Computer Science 2025-09-18 Zhirui Huang , Rui Ma , Shijie Cao , Ran Shu , Ian Wang , Ting Cao , Chixiao Chen , Yongqiang Xiong

Deploying Large Language Models (LLMs) on edge devices remains challenging due to their quadratically increasing computations with the sequence length. Existing studies for dynamic attention pruning are designed for hardware with massively…

Artificial Intelligence · Computer Science 2025-07-29 Jiawen Qi , Chang Gao , Zhaochun Ren , Qinyu Chen

Large language models (LLMs) have demonstrated remarkable performance across a wide range of language processing tasks. However, this success comes at the cost of substantial computation and memory requirements, which significantly impedes…

Machine Learning · Computer Science 2026-01-21 Fen-Yu Hsieh , Yun-Chang Teng , Ding-Yong Hong , Jan-Jan Wu

The Transformer architecture has significantly advanced natural language processing (NLP) and has been foundational in developing large language models (LLMs) such as LLaMA and OPT, which have come to dominate a broad range of NLP tasks.…

Artificial Intelligence · Computer Science 2024-03-27 Youpeng Zhao , Di Wu , Jun Wang