LogQuant: Log-Distributed 2-Bit Quantization of KV Cache with Superior Accuracy Preservation
This addresses memory bottlenecks in LLM inference for users needing efficient deployment, though it appears incremental as it builds on existing quantization methods with a novel filtering approach.
The paper tackles the problem of memory inefficiency in large language model inference by introducing LogQuant, a 2-bit quantization technique for KV Cache that reduces memory usage while preserving performance, achieving up to 200% accuracy improvement on challenging tasks and enhancing throughput by 25% with a 60% batch size increase.
We introduce LogQuant, a groundbreaking 2-bit quantization technique for KV Cache in large language model (LLM) inference, delivering substantial memory savings while preserving superior performance. Previous methods either assume that later tokens are more important or attempt to predict important tokens based on earlier attention patterns. Both approaches, however, can result in performance bottlenecks or frequent mispredictions. LogQuant takes a different approach. By applying a log-based filtering mechanism, it selectively compresses the KV Cache across the entire context, achieving better performance with the same or even reduced memory footprint compared to existing methods. In benchmark tests, it enhances throughput by 25% and boosts batch size by 60% without increasing memory consumption. For challenging tasks such as Math and Code Completion, LogQuant improves accuracy by 40% to 200% at the same compression ratio, outperforming comparable techniques.LogQuant integrates effortlessly with popular inference frameworks like Python's transformers library. Implementation can be available in https://github.com/Concyclics/LogQuantKV.