CASP: Compression of Large Multimodal Models Based on Attention Sparsity
This addresses the need for efficient deployment of large multimodal models, though it is incremental as it builds on existing quantization techniques.
The paper tackles the problem of compressing Large Multimodal Models (LMMs) by exploiting attention sparsity, achieving an average 21% improvement over state-of-the-art 2-bit quantization methods on image- and video-language benchmarks.
In this work, we propose an extreme compression technique for Large Multimodal Models (LMMs). While previous studies have explored quantization as an efficient post-training compression method for Large Language Models (LLMs), low-bit compression for multimodal models remains under-explored. The redundant nature of inputs in multimodal models results in a highly sparse attention matrix. We theoretically and experimentally demonstrate that the attention matrix's sparsity bounds the compression error of the Query and Key weight matrices. Based on this, we introduce CASP, a model compression technique for LMMs. Our approach performs a data-aware low-rank decomposition on the Query and Key weight matrix, followed by quantization across all layers based on an optimal bit allocation process. CASP is compatible with any quantization technique and enhances state-of-the-art 2-bit quantization methods (AQLM and QuIP#) by an average of 21% on image- and video-language benchmarks.