Dezhi Yi
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Distributed×1
Frequent co-authors
Research Timeline
2026
DPIFrame: A Dual-Level Parallelism Acceleration Framework for CTR Model Inference
This paper proposes DPIFrame, a dual parallelizable framework for accelerating Click-through rate (CTR) model inference on GPU, achieving state-of-the-art inference performance with significant speedups.
Highlighted terms show continued research focus across papers
Papers
cs.DCEmpiricalRecentJun 19, 2026
DPIFrame: A Dual-Level Parallelism Acceleration Framework for CTR Model Inference
Dezhi Yi, Huifeng Guo, Kunpeng Xie, Zhaolong Jian +5 more
This paper proposes DPIFrame, a dual parallelizable framework for accelerating Click-through rate (CTR) model inference on GPU, achieving state-of-the-art inference performance with significant speedu…
View →