ClusterGen: Token Generation in Sublinear Time and Memory with Clustering KV Cache

Despite the significant success of large language models (LLMs), their extensive memory requirements pose challenges for deploying them in long-context token generation. The substantial memory footprint of LLM decoders arises from the necessity to store all previous tokens in the attention module, a requirement imposed by key-value (KV) caching. In this work, our focus is on developing an efficient compression technique for the KV cache. Empirical evidence indicates a significant clustering tendency within key embeddings in the attention module. Building on this key insight, we have devised a novel caching method with sublinear complexity, employing online clustering on key tokens and online l2 sampling on values. The result is a provably accurate and efficient attention decoding algorithm, termed ClusterGen. Not only does this algorithm ensure a sublinear memory footprint and sublinear time complexity, but we also establish a tight error bound for our approach.Empirical evaluations on long-context question-answering tasks demonstrate that ClusterGen significantly outperforms existing and state-of-the-art KV cache compression methods in terms of performance and efficiency.