LogQuant: Log-Distributed 2-Bit Quantization of KV Cache with Superior Accuracy Preservation
Keywords: Large Language Models, KV Cache, Memory Efficiency, Quantization
Abstract: 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 \texttt{transformers} library and will be made open-source upon publication.
Supplementary Material: zip
Primary Area: infrastructure, software libraries, hardware, systems, etc.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 6683
Loading