KV Pareto: Systems-Level Optimization of KV Cache and Model Compression for Long Context Inference

Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 5: Industry Track) 2026 Open access

Read full text
Authors: Sai Gokhale, Devleena Das, Rajeev Patwari, Ashish Sirasao, Elliott Delaye
DOI: 10.18653/v1/2026.eacl-industry.9
Cited by: 2

Abstract

Sai Gokhale, Devleena Das, Rajeev Patwari, Ashish Sirasao, Elliott Delaye. Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 5: Industry Track). 2026.

Fields of Study & Subjects

Parallel Computing and Optimization Techniques Advanced Data Storage Technologies Advanced Data Compression Techniques

Publication details

Journal / source
Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 5: Industry Track)
Publisher
Association for Computational Linguistics
Pages
119–131
Publication date
1 January 2026