Siheng Pan, Shaolong Li, Minwei Zhang, Shuxi Guo, Haifeng Sun 0001, Qi Qi 0001, Zirui Zhuang, Xiang Yang, Chunyang Jiang, Jianxin Liao, Jing Wang 0039. RecFlow: Unlocking GPU Efficiency for DLRM Inference via Fine-Grained Parallelism and Incremental Batching. In IEEE INFOCOM 2026 - IEEE Conference on Computer Communications, Tokyo, Japan, May 18-21, 2026. pages 1-10, IEEE, 2026. [doi]
@inproceedings{PanLZGSQZYJLW26,
title = {RecFlow: Unlocking GPU Efficiency for DLRM Inference via Fine-Grained Parallelism and Incremental Batching},
author = {Siheng Pan and Shaolong Li and Minwei Zhang and Shuxi Guo and Haifeng Sun 0001 and Qi Qi 0001 and Zirui Zhuang and Xiang Yang and Chunyang Jiang and Jianxin Liao and Jing Wang 0039},
year = {2026},
doi = {10.1109/INFOCOM59046.2026.11571693},
url = {https://doi.org/10.1109/INFOCOM59046.2026.11571693},
researchr = {https://researchr.org/publication/PanLZGSQZYJLW26},
cites = {0},
citedby = {0},
pages = {1-10},
booktitle = {IEEE INFOCOM 2026 - IEEE Conference on Computer Communications, Tokyo, Japan, May 18-21, 2026},
publisher = {IEEE},
isbn = {979-8-3315-4961-9},
}