一作INFOCOM 2026Oral· Computer Communications & Networking
RecFlow: Unlocking GPU Efficiency for DLRM Inference via Fine-Grained Parallelism and Incremental Batching
Siheng Pan · Shaolong Li · Minwei Zhang · Shuxi Guo · Haifeng Sun · Qi Qi · Zirui Zhuang · Xiang Yang · Chunyang Jiang · Jianxin Liao · Jing Wang
效率与系统OpenReview