paper-with-me

홈 › Papers

Enhancing Inference Efficiency of Large Language Models: Investigating Optimization Strategies and Architectural Innovations

2024-04-02 · Georgy Tyukin

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 performance of larger models, but with a reduced cost of running them. In this thesis we explore the methods of model compression, and we empirically demonstrate that the simple method of skipping latter attention sublayers in Transformer LLMs is an effective method of model compression, as these layers prove to be redundant, whilst also being incredibly computationally expensive. We observed a 21% speed increase in one-token generation for Llama 2 7B, whilst surprisingly and unexpectedly improving performance over several common benchmarks.

📄 PDF Abstract BibTeX arXiv:2404.05741

Code (0)

등록된 구현이 없습니다.

Tasks

Model Compression

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
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…
Residual Connection 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

CUTE: A Multilingual Dataset for Enhancing Cross-Lingual Knowledge Transfer in Low-Resource Languages

2025-09-21 · Wenhao Zhuang, Yuan Sun arxiv

Large Language Models (LLMs) demonstrate exceptional zero-shot capabilities in various NLP tasks, significantly enhancing user experience and efficiency. However, this advantage is primarily limited to resource-rich lang…

Cross-Lingual TransferMachine Translation

Investigating Execution-Aware Language Models for Code Optimization

2025-03-11 · Federico Di Menna, Luca Traini, Gabriele Bavota, Vittorio Cortellessa

Code optimization is the process of enhancing code efficiency, while preserving its intended functionality. This process often requires a deep understanding of the code execution behavior at run-time to identify and addr…

A Comprehensive Solution to Connect Speech Encoder and Large Language Model for ASR

2024-06-25 · Van Tung Pham, Yist Lin, Tao Han, Wei Li 외

Recent works have shown promising results in connecting speech encoders to large language models (LLMs) for speech recognition. However, several limitations persist, including limited fine-tuning options, a lack of mecha…

Language ModelingLanguage ModellingLarge Language Modelspeech-recognition+1

Think Deep, Think Fast: Investigating Efficiency of Verifier-free Inference-time-scaling Methods

2025-04-18 · Junlin Wang, Shang Zhu, Jon Saad-Falcon, Ben Athiwaratkun 외

There is intense interest in investigating how inference time compute (ITC) (e.g. repeated sampling, refinements, etc) can improve large language model (LLM) capabilities. At the same time, recent breakthroughs in reason…

Large Language Model

Compressing KV Cache for Long-Context LLM Inference with Inter-Layer Attention Similarity

2024-12-03 · Da Ma, Lu Chen, Situo Zhang, Yuxun Miao 외

The increasing context window size in Large Language Models (LLMs), such as the GPT and LLaMA series, has improved their ability to tackle complex, long-text tasks, but at the cost of inference efficiency, particularly r…

Text Generation