CSR: Achieving 1 Bit Key-Value Cache via Sparse Representation

Abstract

The emergence of long-context text applications utilizing large language models (LLMs) has presented significant scalability challenges, particularly in memory footprint. The linear growth of the Key-Value (KV) cache, which stores attention keys and values to reduce redundant computations, can significantly increase memory usage and may prevent models from functioning properly in memory-constrained environments. To address this issue, we propose a novel approach called Cache Sparse Representation (CSR), which converts the KV cache by transforming the dense Key-Value cache tensor into sparse indexes and weights, offering a more memory-efficient representation during LLM inference. Furthermore, we introduce NeuralDict, a novel neural network-based method to automatically generate the dictionary used in our sparse representation. Our extensive experiments demonstrate that CSR matches the performance of state-of-the-art KV cache quantization algorithms while ensuring robust functionality in memory-constrained environments.