AISep 25, 2024

Search for Efficient Large Language Models

Harvard
arXiv:2409.17372v216 citationsh-index: 18Has Code
Originality Incremental advance
AI Analysis

This work addresses the need for more efficient LLMs in AI applications by focusing on architecture optimization, though it is incremental as it builds on existing compression techniques.

The paper tackles the problem of inefficient large language models (LLMs) by proposing a training-free architecture search framework to identify optimal subnets, achieving inference acceleration and superior performance compared to state-of-the-art training-free structured pruning methods on standard benchmarks.

Large Language Models (LLMs) have long held sway in the realms of artificial intelligence research. Numerous efficient techniques, including weight pruning, quantization, and distillation, have been embraced to compress LLMs, targeting memory reduction and inference acceleration, which underscore the redundancy in LLMs. However, most model compression techniques concentrate on weight optimization, overlooking the exploration of optimal architectures. Besides, traditional architecture search methods, limited by the elevated complexity with extensive parameters, struggle to demonstrate their effectiveness on LLMs. In this paper, we propose a training-free architecture search framework to identify optimal subnets that preserve the fundamental strengths of the original LLMs while achieving inference acceleration. Furthermore, after generating subnets that inherit specific weights from the original LLMs, we introduce a reformation algorithm that utilizes the omitted weights to rectify the inherited weights with a small amount of calibration data. Compared with SOTA training-free structured pruning works that can generate smaller networks, our method demonstrates superior performance across standard benchmarks. Furthermore, our generated subnets can directly reduce the usage of GPU memory and achieve inference acceleration. Code: https://github.com/shawnricecake/search-llm

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes