FASP: Fast and Accurate Structured Pruning of Large Language Models
This provides a practical solution for optimizing LLMs for deployment on resource-constrained devices, though it is incremental as it builds on existing structured pruning techniques.
The paper tackles the computational and memory demands of large language models (LLMs) by introducing FASP, a structured pruning framework that reduces model size while preserving performance, achieving pruning of OPT-125M in 17 seconds and LLaMA-30B in 15 minutes with superior perplexity and accuracy compared to state-of-the-art methods.
The rapid increase in the size of large language models (LLMs) has significantly escalated their computational and memory demands, posing challenges for efficient deployment, especially on resource-constrained devices. Structured pruning has emerged as an effective model compression method that can reduce these demands while preserving performance. In this paper, we introduce FASP (Fast and Accurate Structured Pruning), a novel structured pruning framework for LLMs that emphasizes both speed and accuracy. FASP employs a distinctive pruning structure that interlinks sequential layers, allowing for the removal of columns in one layer while simultaneously eliminating corresponding rows in the preceding layer without incurring additional performance loss. The pruning metric, inspired by Wanda, is computationally efficient and effectively selects components to prune. Additionally, we propose a restoration mechanism that enhances model fidelity by adjusting the remaining weights post-pruning. We evaluate FASP on the OPT and LLaMA model families, demonstrating superior performance in terms of perplexity and accuracy on downstream tasks compared to state-of-the-art methods. Our approach achieves significant speed-ups, pruning models such as OPT-125M in 17 seconds and LLaMA-30B in 15 minutes on a single NVIDIA RTX 4090 GPU, making it a highly practical solution for optimizing LLMs.