KVSwap: Disk-aware KV Cache Offloading for Long-Context On-device Inference

Read full text Summarise with VIRAT
Authors: Huawei Zhang
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This code artifact serves as a supporting component for the paper titled "KVSwap: Disk-aware KV Cache Offloading for Long-Context On-device Inference." For the most current release of KVSwap, please visit GitHub: https://github.com/hwhwz23/KVSWAP-CODE.git

Fields of Study & Subjects

Parallel Computing and Optimization Techniques Advanced Neural Network Applications Natural Language Processing Techniques

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
20 March 2026
Language
EN