GPTGet
排序: 最新 热门 引用
全部 Artificial Intelligence Computation and Language Computer Vision Information Retrieval Machine Learning Machine Learning (Stats) Neural and Evolutionary Computing Robotics
cs.IR 2603.11486

Quantized Inference for OneRec-V2

OneRec-V2通过FP8量化推理实现49%延迟减少和92%吞吐量提升。

Yi Su, Xinchen Luo, Hongtao Cheng 等

2026-03-12 50