Author

Hong Zhang

Observed name: Zhang, Hong

Institution: University of Waterloo

Observed institution: University of Waterloo

OpenAlex ID: A5160199697

GearUp: DAG-aware Acceleration for Serverless Inference Serving via Slack-guided Pre-loading

2026 · Qi, Qi, Sui, Yifan, et al. · arXiv (Cornell University)

ConfluxServe: Reconciling Resource Utilization and Parallelism Efficiency across Prefill and Decode in LLM Serving

2026 · Chen, Wenhao, Zhang, Hong · arXiv (Cornell University)

Works count: 2

Citation count:

H-index:

I10-index: