Work

TARDIS: A GPU-Centric KV Cache Service for Efficient LLM Inference

Year: 2025

Type: conference-paper

Source: ACM SIGOPS Asia-Pacific Workshop on Systems (APSys)

DOI: 10.1145/3725783.3764393

Authors: Yifan Hu, Shi Qiu, Jianqin Yan, Hao Chen, Xintao Wang, Tang Lu, Guangtao Xue, Yiming Zhang

Institutions: Xiamen University, Shanghai Jiao Tong University

Language: English

Topic: Parallel Computing and Optimization Techniques

Subfield: Hardware and Architecture

Field: Computer Science

Domain: Physical Sciences

Open Access status: closed

OpenAlex ID: W4415003901

FWCI: 1.814

Cites: 8

Cited by: 2

Related to: