activity
20212024
most citedOliVe: Accelerating Large Language Models via Hardware-friendly Outlier-Victim Pair Quantization

150 citations · 178 across the 22 of their papers we have counts for

collaborators
Showing 2023 · cs.DBShow all

1 paper · 2 filters

cs.DB2023

Async-fork: Mitigating Query Latency Spikes Incurred by the Fork-based Snapshot Mechanism from the OS Level

Pu Pang, Gang Deng, Kaihao Bai +12

In-memory key-value stores (IMKVSes) serve many online applications because of their efficiency. To support data backup, popular industrial IMKVSes periodically take a point-in-tim…