SliceGPT: Compress Large Language Models by Deleting Rows and Columns

Large language models have become the cornerstone of natural language processing, but their use comes with substantial costs in terms of compute and memory resources. Sparsification provides a solution to alleviate these resource constraints, and recent works have shown that trained models can be sparsified post-hoc. Existing sparsification techniques face challenges as they need additional data structures and offer constrained speedup with current hardware. In this paper we present SliceGPT, a new post-training sparsification scheme which replaces each weight matrix with a smaller (dense) matrix, reducing the embedding dimension of the network. We offer a new insight, computational invariance in transformer networks, which enables SliceGPT and we hope it will inspire and enable future avenues to reduce memory and computation demands for pre-trained models. Large language models (LLMs) are neural networks with billions of parameters, trained on trillions of tokens (Zhao et al., 2023). The cost of training an LLM has caused a shift to re-using pre-trained models for multiple tasks, the foundation model paradigm. The size of LLMs makes deploying a pre-trained model an expensive undertaking. Many models require multiple GPUs to be able to compute a prediction, and because the models are autoregressive, multiple forward passes of the neural network are needed to generate text responses.