LOP: Learning Optimal Pruning for Efficient On-Demand MLLMs Scaling
By: Zhihan Zhang , Xiang Pan , Hongchen Wei and more
Potential Business Impact:
Makes smart computer programs smaller and faster.
Structural pruning techniques are essential for deploying multimodal large language models (MLLMs) across various hardware platforms, from edge devices to cloud servers. However, current pruning methods typically determine optimal strategies through iterative search processes, resulting in substantial computational overhead for on-demand MLLMs adaptation. To address this challenge, we propose LOP, an efficient neural pruning framework that learns optimal pruning strategies from the target pruning constraint, eliminating the need for computationally expensive search-based methods. LOP approach trains autoregressive neural networks (NNs) to directly predict layer-wise pruning strategies adaptive to the target pruning constraint, eliminating the time-consuming iterative searches. Experimental results across multiple tasks show that LOP outperforms state-of-the-art pruning methods in various metrics while achieving up to three orders of magnitude speedup.
Similar Papers
Breaking Expert Knowledge Limits: Self-Pruning for Large Language Models
CV and Pattern Recognition
Lets computers shrink themselves to work better.
Efficient LLMs with AMP: Attention Heads and MLP Pruning
Machine Learning (CS)
Makes smart computer programs run faster and smaller.
FastForward Pruning: Efficient LLM Pruning via Single-Step Reinforcement Learning
Machine Learning (CS)
Makes AI models smaller and faster to train.