Work

Q-Filters: Leveraging Query-Key Geometry for Efficient Key-Value Cache Compression

Year: 2025

Type: conference-paper

Abstract: This work was granted access to the HPC resources of IDRIS under the allocation 2024-AD011013680R2 made by GENCI.

Source: HAL (Le Centre pour la Communication Scientifique Directe)

Authors: Godey, Nathan, Devoto, Alessio, Zhao, Yu, Scardapane, Simone, Minervini, Pasquale, de la Clergerie, Éric, Sagot, Benoît

Institutions: ALMANACH: Modélisation et analyse linguistique automatique et humanités computationnelles, Sapienza University of Rome, University of Edinburgh

Language: English

Topic: Parallel Computing and Optimization Techniques

Subfield: Hardware and Architecture

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W7130246380

FWCI:

Cites:

Cited by:

Related to: