A Method for Building Large Language Models with Predefined KV Cache Capacity
This addresses memory efficiency issues for developers and users of large language models, though it appears incremental as it builds on existing Transformer architectures.
The paper tackles the problem of excessive memory consumption in large language models by introducing the Bounded-Cache Transformer (BCT), which uses a bounded-length KV cache to significantly reduce memory usage while maintaining inference quality and system throughput.
This paper introduces a novel approach, the Bounded-Cache Transformer (BCT), for building large language models with a predefined Key-Value (KV) cache capacity. The BCT addresses the excessive memory consumption issue in traditional KV caches by implementing a bounded-length KV cache, which is particularly suitable for the attention layers in Transformer decode-only architectures. By dynamically updating the key-value vector sequences, the BCT achieves efficient inference within limited cache capacity, significantly reducing memory usage while maintaining model performance and system throughput. Experimental results demonstrate that the BCT significantly reduces memory usage while maintaining the model's inference quality, offering a new solution for efficient inference in large language models.