paper-with-me

Papers

Faster and Lighter LLMs: A Survey on Current Challenges and Way Forward

2024-02-02 · Arnav Chavan, Raghav Magazine, Shubham Kushwaha, Mérouane Debbah, Deepak Gupta

Despite the impressive performance of LLMs, their widespread adoption faces challenges due to substantial computational and memory requirements during inference. Recent advancements in model compression and system-level optimization methods aim to enhance LLM inference. This survey offers an overview of these methods, emphasizing recent developments. Through experiments on LLaMA(/2)-7B, we evaluate various compression techniques, providing practical insights for efficient LLM deployment in a unified setting. The empirical analysis on LLaMA(/2)-7B highlights the effectiveness of these methods. Drawing from survey insights, we identify current limitations and discuss potential future directions to improve LLM inference efficiency. We release the codebase to reproduce the results presented in this paper at https://github.com/nyunAI/Faster-LLM-Survey

📄 PDF Abstract BibTeX arXiv:2402.01799

Code (1)

nyunai/faster-llm-survey 공식 구현 pytorch

Tasks

Model CompressionSurvey

Similar Papers 제목 키워드 기반

A Practical Survey on Faster and Lighter Transformers

2021-03-26 · Quentin Fournier, Gaétan Marceau Caron, Daniel Aloise

Recurrent neural networks are effective models to process sequences. However, they are unable to learn long-term dependencies because of their inherent sequential nature. As a solution, Vaswani et al. introduced the Tran…

Knowledge DistillationSurvey

A multitask deep learning model for real-time deployment in embedded systems

2017-10-31 · Miquel Martí, Atsuto Maki

We propose an approach to Multitask Learning (MTL) to make deep learning models faster and lighter for applications in which multiple tasks need to be solved simultaneously, which is particularly useful in embedded, real…

object-detectionObject DetectionSemantic Segmentation

Prompt Highlighter: Interactive Control for Multi-Modal LLMs

2023-12-07 · CVPR 2024 1 · Yuechen Zhang, Shengju Qian, Bohao Peng, Shu Liu 외

This study targets a critical aspect of multi-modal LLMs' (LLMs&VLMs) inference: explicit controllable text generation. Multi-modal LLMs empower multi-modality understanding with the capability of semantic generation yet…

MMEText Generation

Large Language Models for Code Generation: A Comprehensive Survey of Challenges, Techniques, Evaluation, and Applications

2025-03-03 · Nam Huynh, Beiyu Lin

Large Language Models (LLMs) have demonstrated their remarkable capabilities in numerous fields. This survey focuses on how LLMs empower users, regardless of their technical background, to use human languages to automati…

Code GenerationSurvey

Reinforcement Learning Enhanced LLMs: A Survey

2024-12-05 · Shuhe Wang, Shengyu Zhang, Jie Zhang, Runyi Hu 외

This paper surveys research in the rapidly growing field of enhancing large language models (LLMs) with reinforcement learning (RL), a technique that enables LLMs to improve their performance by receiving feedback in the…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Survey